Qualification: 
Ph.D
s_veni[at]cb[dot]amrita[dot]edu
Phone: 
+91 422 2685000 Ext. 5723

Dr. S. Veni joined Amrita Vishwa Vidyapeetham as a faculty in the year 2001 under the Department of Electronics and Communication Engineering, with 8 years of experience in the field of teaching. She is currently working as Associate Professor. She received her AMIE degree from Institution of Engineers, Calcutta, in the year 1994 and M. E. degree (Applied Electronics) from Bharathiar University, Coimbatore, in the year 1998. She obtained her Ph. D. degree in the area of Image Processing from Amrita Vishwa Vidyapeetham in January 2012. Her areas of interest include Signal and Image Processing, Hardware Implementation of Signal and Image Processing Algorithms. She has published nearly 50 papers in international journals and conferences. Also, she has guided more than 30 projects for both PG and UG students.

She has received best paper award four times for the papers she had presented in the conferences and also cash awards from Amrita Vishwa Vidyapeetham for her publications. She is an Associate Member in the Institution of Engineers, Member in ISTE, Member in IETE, BOS member, Doctoral Committee Member (Amrita Vishwa Vidyapeetham, Anna University, Karunya University and Kerala Agricultural University), Academic Community Member in International Congress for global Science and Technology (ICGST). She has served as a reviewer and session chair in the International conferences, reviewer in reputed journals like Inderscience, IET Image Processing and also as an expert member for the faculty recruitment process held at engineering colleges outside Amrita. She has delivered nearly 10 invited lectures in various Engineering and Polytechnic colleges. She has organized several national workshops in association with CoreEl Technologies, Bangalore and ISRO sponsored national seminar. She has been the Co-ordinator for M.Tech Communication Engineering and signal Processing from 2014-2016.

Education

  • 2012: Ph. D. in Image processing
    Amrita Vishwa Vidyapeetham
  • 1998: M. E. in Applied Electronics
    Bharathiar University

Professional Experience

Year Affiliation
March 2012 - Till Date Associate Professor, Amrita Vishwa Vidyapeetham
Domain : Teaching, Research and Projects
July 2006 - February 2012 Assistant Professor, Amrita Vishwa Vidyapeetham
Domain : Teaching, Research and Projects
January 2003 - June 2006 Senior Lecturer, Amrita Vishwa Vidyapeetham
Domain : Teaching, Research and Projects
February 2001 - December 2002 Lecturer, Amrita Vishwa Vidyapeetham
Domain : Teaching and Projects
May 1999 - February 2001 Lecturer, Karunya Institute of Technology
Domain : Teaching and Projects

Academic Responsibilities

SNo Position Class / Batch Responsibility
1. Class Counselor ECE ‘A’2000-2004 Mentoring students
2. Class Advisor EIE 2004-2008 ECE ‘C’ 2018-2022 Mentoring students
3. Class Advisor and Year Co-ordinator ECE 2010-2014 Mentoring students, Project coordination
4. PG Co-ordinator M.Tech CSP 2014-2016 Admission process, Mentoring students, Project Co-ordinator
5. BOS Member M.Tech CSP 2014 Framing Syllabus
6 BOS Member M.Tech CSP 2016 Syllabus Revision
7 BOS Member M.Tech CS 2019 Framing Syllabus
7 Department NAAC Co-ordinator 2014 Collection of data and preparation of files
8 Ph.D admission Co-ordinator Dec 2015 Question paper setting, Conducting Interview

Undergraduate Courses Handled

  1. Signal Processing I
  2. Digital Signal Processing
  3. Image processing
  4. Biomedical Instrumentation
  5. Electronic Measurements and Instrumentation
  6. Sparse signal and image Processing
  7. Wavelet based Signal Processing and Applications
  8. Digital System Design
  9. Image and Video Processing
  10. Industrial Instrumentation
  11. Data Communication

Post-Graduate / PhD Courses Handled

  1. Signal Processing (M.Tech CSP)
  2. Image and Video Processing (M.Tech CSP and M.Tech Automotive Electronics)
  3. Biomedical Image Processing (M.Tech BME)
  4. Machine Learning (M.Tech CSP)
  5. Hardware Description Languages (M.Tech VLSI Design)
  6. Computer Aided Design of VLSI Algorithms (M.Tech VLSI Design)
  7. Image Processing (M.Tech CVIP)

Specialized Courses Developed

  • Sparse Signal and Image Processing
  • Hyperspectral Image Processing

Participation in Faculty Development / STTP / Workshops /Conferences

SNo Title Organization Period Outcome
1. TEQIP-II Sponsored workshop on Machine Learning and its applications to contemporary PSG college of Technology September 8 - 10, 2016 Handled course in Machine Learning for PG students, Guided Projects
2. National workshop on SDR & Strategic Applications (SDRSA 2016) Amrita School of Engineering, Coimbatore January 21 - 22, 2016 Guided UG and PG Projects
3. Complementary seminar – MATLAB & Simulink for Engineering Education CoreEL Technologies, Bangalore February 10, 2015 Guided UG and PG Projects
4 Two-week ISTE Workshop on Signals & Systems Indian Institute of Technology, Kharagpur January 2 - 12, 2014 Updated the concepts and was useful for teaching
5 National Workshop on “Hands on Training in Signal & Image Processing Applications using Xilinx System Generator Sri Ramakrishna Engineering College, Coimbatore. August 22 - 23,  2013 Developed contact Resource persons in with CoreEl Technology and conducted series of workshops
6 ISTE-SRM sponsored short term training programme on “Sparse theory and applications to signal and Image Processing” Kongu Engineering College, Perundurai, Erode. May 2 - 13, 2013 Designed curriculam for the subject “Sparse Signal and Image Processing”, Project Guidance
7 International Conference on Intelligent sensing and information Processing (ICISIP) Melbourn University and IEEE January 4 - 7, 2005 Participated and presented paper
8 IEEE conference INDICON 2005 IIT Madras December 11 - 13,  2005 Participated and presented paper
9 National Conference on Emerging Trends in VLSI Design and Testing PSG College of technology February 21 - 22, 2003 Participated and presented paper
10 STTP Programme on “Neural Networks, Fuzzy Logic and its Applications to Information Processing Technology” RVS College of Engineering, Dindigul June 23 - 27,  2003 Guided UG and PG Projects
11 National workshop on Computer vision, Graphics and Image processing Thiagarajar college of Engg, Madurai February 15 - 16, 2002 Participated and presented paper
12 National conference on Emerging Trends in Engineering Design Automation MNM Jain Engineering College, Chennai. February 23 - 24,  2001 Participated and presented paper
13 National Conference of Advanced Computing PSG College of technology February 2 - 3, 2001 Participated and presented paper
14 One-day workshop on ‘Teaching-Learning process’ Karunya Institute of Technology, Coimbatore May 14, 2000 Useful for developing teaching skills
15 Two days workshop on ‘Neuro-Fuzzy-Genetic Systems’ kumaraguru Institute of Technology, Coimbatore March 3 - 4, 2000 Guided UG and PG Projects
16 One week Faculty Development programme Karunya Institute of Technology, Coimbatore May 14 - 18, 1999 Useful for developing teaching skills

Organizing Faculty Development / STTP / Workshops /Conferences

SNo Title Organization Period Outcome
1. National Workshop on Role of University in Empowering Indian Villages ISRO, ASE, Cbe September 21 - 23, 2016 Developed contacts with the resource persons and submitted the project proposal
2. National seminar on “Techniques and Applications of Hyperspectral Image analysis” ISRO, ASE, Cbe April 19 - 20, 2016 Developed contacts with the resource persons and submitted the project proposal
3. National level workshop on “Xilinx Vivado System Generator and Analog Discovery Kit” ASE, Cbe, CoreEl Technologies, Bangalore September 21 - 22, 2015 PG and UG projects
4. National level workshop on “Embedded Design Flow using Xilinx ZynQSoC” ASE, Cbe, CoreEl Technologies, Bangalore February 27 - 28, 2015 PG and UG projects
5 Hands-on Training on “Signal Processing Applications using Vivado System Generator” ASE, Cbe, CoreEl Technologies, Bangalore November 10 - 11, 2014 Setup of DSP hardware lab PG and UG projects
6 Two days National level workshop on “Signal and Image Processing Applications using Xilinx System Generator” ASE, Cbe, CoreEl Technologies, Bangalore April 10 - 11,  2014 PG and UG projects
7 One day training program for faculty on “Image Processing using Xilinx System Generator” ASE, Cbe, CoreEl Technologies, Bangalore February 14, 2014 Useful for faculty to guide the projects
8 National level workshop on “Advances in Signal and Image Processing“ Amrita School of Engineering, Coimbatore May 29 - June 2, 2012 Updation of recent Technologies

Academic Research – PhD Guidance

SNo Name of the Scholar Specialization / Title Duration / Registration Status / Year
1. Abhishek.S Specialization: Signal Processing Title: Algorithm Development for Sensing and Reconstruction in Compressed SensingApplied to ECG Signal Processing Registration January 2013 Graduated 2018
2. V.Kamalaveni Specialization: Image Processing Title: Algorithm Development for Edge Preserving Image Denoising using VariationalCalculus and Partial Differential Equation Based Models Registration January 2011 Thesis submitted
3 C. B. Rajesh Specialization: Image Processing Title: Algorithm development for the crop assessment using hyper  spectral images Registration January 2016 Completed Comprehensive Examination
4 P. Sreevidya Specialization: Image Processing Title:Algorithm development for multimodal emotional recognition July 2018 Doing course work
5 R.Anand Hyperspectral Image Processing Dec 2018 Doing course work

Academic Research – PG Projects

SNo Name of the Scholar Programme Specialization Duration Status
1 Mayura. N.P M.Tech CSP Hyper Spectral Image Processing 2017-2019 Ongoing
2 Mirunalini M.Tech Automotive Electronics Image Processing 2017-2019 Ongoing
3 KadambariSaiKiran M.Tech CSP Speech Signal Processing 2016-2018 Completed
4 SreedeviPrabhakaran M.Tech CSP Image Processing and Machine Learning 2016-2018 Completed
5 ShaliniAnant M.Tech Automotive Electronics Image Processing, Machine leraning 2016-2018 Completed
6 Edwin Joze M.Tech Automotive Electronics Image Processing 2016-2018 Completed
7 Santhosh B M.Tech Automotive Systems Video Processing 2016-2018 Completed
8 Krithika P M.Tech CSP Image Processing 2015-2017 Completed
9 Anand. R M.Tech CSP Hyper Spectral Image Processing 2015-2017 Completed
10 Reshma. s M.Tech CSP Hyper Spectral Image Processing 2015-2017 Completed
11 Arun Das. S M.Tech CSP Speech Signal Processing 2014-2016 Completed
12 Thushara. S M.Tech CSP Video Processing 2014-2016 Completed
13 Jayaprakash. S M.Tech Automotive Systems Image Processing 2014-2016 Completed

Projects Under Review

SNo Title Agency Amount Date of Submission Status
1. Intelligent Decision Making System for Smart Farming DST (SERB,CRG) 18.07 Lakhs 30th June 2018 Under Review
2. Developing a mathematical model for CS based ECG signal Compression DST (SERB) 6 Lakhs 31st March 2018 Under Review
3. Advanced Algorithms for 3D Modeling using hyperspectral and LiDAR Data under Urban Environment ISRO Respond 25.38 Lakhs 29th November 2018 Under Review

Project Contest:

The project titled “Hexagonal Pixel Grid Modeling For Edge Detection and Image Skeletanization”  has been selected and presented for  the Innovate design contest  organized by  Altera and BITS Pilani  during April 2007. Altera Quartus FPGA board worth Rs.25000/- was received as prize.

Research Expertise

To pursue the research in the following fields of interest through funded projects, guiding UG/PG/Ph.D students

  • Developing a real time compressive sensing system for signal and Image Processing applications
  • Developing active learning methods and classification techniques for Hyper Spectral Image Processing
  • Developing Technology for Agriculture  which includes Signal and Image Processing
  • Hardware Implementation of Signal and Image Processing Algorithms
  • Hexagonal Image Processing

UG / PG Student Projects

  1. Lane detection of Images using Hough transform
  2. Efficient Image segmentation during uneven illumination
  3. Hardware Implementation of EZW algorithm
  4. Hardware Implementation of circular Hough Transform
  5. Hardware Implementation of Bio retinal image Encoder
  6. Shape matching for Object in complex images
  7. Edge detection and segmentation using Gabor filters
  8. Hardware implementation of Hexagonal pixel grid modeling for edge detection
  9. Hardware implementation of Hexagonal pixel grid modeling for skeletonization
  10. Design of  Cellular array processor using Hexagonal pixel grid modeling for edge detection and skeletonization
  11. Boundary contour system modeling for dynamic compression and image edge enhancement
  12. Color Image compression for Limited Displays using  self organising feature map
  13. Analysis of Interpolation Kernels For Hexagonal Lattices
  14. Multiresolution Image Processing Using Hexagonal Wavelets
  15. Analysis of Edge detection techniques on Rectangular and Hexagonal Sampled Grids

Teaching

  • Image and Video Processing
  • Digital Signal Processing
  • Sparse signal and image Processing
  • Wavelet based Signal Processing and Applications
  • Digital System Design
  • Image Analysis

Workshops Organized

  • Two days ISRO sponsored National seminar on “Techniques and Applications of Hyperspectral Image analysis” during 19-20th April 2016 at Amrita School of Engineering, Coimbatore
  • Two days national level workshop on  “Xilinx Vivado System Generator and Analog Discovery Kit, “ under the agies of  Department of ECE,  Amrita Vishwa Vidyapeetham, Coimbatore in association with CoreEl Technologies, Bangalore during  21-22 Sep 2015
  • Two days National level workshop on “Embedded Design Flow using Xilinx  ZynQ  SoC” under the agies of  Department of ECE,  Amrita Vishwa Vidyapeetham, Coimbatore in association with CoreEl Technologies, Bangalore during 27-28th Feb 2015
  • Two days Hands-on Training on “Signal Processing Applications using Vivado System Generator”  under the agies of  Department of ECE,  Amrita Vishwa Vidyapeetham, Coimbatore in association with CoreEl Technologies, Bangalore during November 10 -11, 2014. 
  • Two days National level workshop on “Signal and Image Processing Applications using Xilinx System Generator” in association with coreEL Technologies, Bangalore during 10-11 April 2014.
  • One day training program for faculty on “Image Processing using Xilinx System Generator” in association with coreEL Technologies, Bangalore on February 14th 2014.
  • Four days IETE sponsored National level workshop on “Advances in Signal and Image Processing“  during May 29th to 2nd June, 2012 at Amrita Vishwa Vidya peetham.
  • Teaching Assistant in the two week ISTE workshop on Basic Electronics conducted by Indian Institute of Technology, Bombay (Under MHRD) from 28th June to 8th July, 2011 at Amrita Vishwa Vidya peetham, Coimbatore

Membership of Scientific and Professional Bodies

  • Board of studies member for the M. Tech Communication Engineering and Signal Processing
  • Doctoral committee member (Amrita Vishwa Vidyapeetham and Anna university)
  • Life Member in ISTE – LM 16259
  • Member in IETE – M174553
  • Associate Member in The Institution of Engineers – AM0893330
  • Academic Community Member in International Congress for Global Science and Technology (ICGST).

Honours and Awards

  • Best paper award for the paper titled “Emotion Recognition from Videos Using Facial Expressions, “ International Conference on Artificial Intelligence and Evolutionary Computations in Engineering Systems (ICAIECES-2016) at SRM University, May 19 - 20, 2016
  • Best paper award for the paper titled, ”Analog VLSI implementation of Cellular Neural Network and its applications to Image Processing,” in the International Conference on Systemics, Cybernatics and Informatics organised by Pentagram Research Centre Pvt  Ltd, Hyderabad during February 12-15, 2004
  • Best paper award for the paper titled “CMOS VLSI implementation of Analog neuron using    PWM technique” in the National Conference on Emerging Trends in VLSI Design and Testing conducted by PSG College of technology during  February 21- 22, 2003
  • Best paper award for the paper titled “Cell locating strategy in personal   communication Networks” at PSG Tech, Coimbatore in the National conference during Feb 2-3, 2001.
  • Cash award for the publications (for three papers) from Amrita Vishwa Vidyapeetham  in the year 2011.

Conferences Attended

  • International Conference on Intelligent sensing and information Processing (ICISIP)” organized by Melbourn University and IEEE, 4-7, Jan 2005
  •  IEEE conference INDICON 2005 at IIT Madras, Chennai during 11-13 Dec 2005.
  • “National Conference on Emerging Trends in VLSI Design and Testing” at PSG College of technology on February 21 and 22, 2003.
  • “National workshop on Computer vision,   Graphics and Image processing” during Feb 15-16, 2002 at Thiagarajar college  of Engg, Madurai.
  • “National conference on Emerging Trends in Engineering Design Automation” during 23, 24th Feb 2001 at MNM Jain Engineering College, Chennai.
  • “National Conference of Advanced Computing “  during Feb 2,3-2001.
     

 Short-term Courses / Trainings Participated

  • Attended the complementary seminar – MATLAB & Simulinkfor Engineering Education on 10/02/2015 at Coimbatore under the track “Teaching signal processing & control system Design using MATLAB & Simulink”
  • Workshop on Space Technology and Sponsored Research by VSSC, ISRO, 25th July 2014 at Amrita Vishwa Vidyapeetham
  • Two-week ISTE Workshop on Signals & Systems conducted by Indian Institute of Technology, Kharagpur which was held under the National Mission on Education through ICT (MHRD) from 2nd to 12th January 2014 at Amrita Vishwa Vidya peetham, Coimbatore.
  • Two days National Workshop on “Hands on Training in Signal & Image Processing Applications using Xilinx System Generator” 22nd & 23rd August 2013 at Sri Ramakrishna Engineering College, Coimbatore.
  • ISTE-SRM sponsored short term training programme on “Sparse theory and applications to signal and Image Processing” from 02.05.2013 to 08.05.2013 at Kongu Engineering College, Perundurai, Erode.
  • ‘Research Retreat’ program at Amrita School of Engineering , Amritapuri on March 28th 2012.
  • 33rd ISTE Convention and National Seminar at Kumaraguru College of       Technology, Coimbatore from 27-10 Dec 2003.
  • STTP Programme on “Neural Networks, Fuzzy Logic and its Applications to Information Processing Technology” at RVS College of Engineering, Dindigul from 23 - 27 June 2003.
  • One-day workshop on ‘Teaching-Learning process’ at Karunya Institute, Coimbatore on May 14th, 2000.
  • Two days workshop on ‘Neuro-Fuzzy-Genetic Systems’ organized by kumaraguru Institute of Technology, Coimbatore during 3 - 4 March 2000.
  • One week Faculty Development programme from May 14th to May18th 1999 at Karunya Institute of Technology, Coimbatore organised by Southern Human Resource Development Agency, Chennai.
  • Three days ISTE workshop on ‘Industry-Institution Interaction’ during  22-24th Dec 1994 at Sree Narayanaguru Institute of Technology, Coimbatore.

Guest Lectures Delivered

  • Delivered Lecture on “Hardware Implementation of image processing algorithms” on 20/02/2015 at Ahaliya school of Engineering, Palakkad
  • Delivered Lecture on “Hardware implementation of signal and video processing Architecture” in the workshop organized by ECE department on 25.01.2013 at Amrita Vishwa Vidya Peetham, Coimbatore.
  • Delivered Guest Lecture on the topic “Research trends in Image Processing” in the one day workshop on Image processing and applications organized by the Department of ECE and Benchmark Systems, Chennai on 14.09.2012 at Sri Krishna College of Engineering and Technology, Coimbatore.
  • Delivered Lecture on the topic  “Image enhancement in spatial domain and Fourier domain in the IETE sponsored National level workshop on “Advances in Signal and Image Processing “ on May 30th, 2012 at Amrita Vishwa Vidyapeetham, Coimbatore.
  • Delivered Lecture on the topic  “Image Processing and its applications” in a Technical Symposium on 10.08.2009 at C.M.S. college of Science and Commerce, Chinnavedampatti, Coimbatore - 641006
  • Resource person in the National Seminar and delivered Lecture on "Budding Trends in VLSI" at RVS College of Arts and Science, Sulur, Coimbatore on March 5th, 2004
  • Guest lecture delivered in the topic "VLSI Design" at Christ the king Institute of Technology, Coimbatore on 12th august, 2003.
  • Guest lecture delivered on the topic, "Recent Trends in Computer communication      Networks” at Sree Narayanaguru Institute of Technology, Coimbatore on 14th August, 2000
  • Delivered lecture on the topic  “Hemodynamic control using Fuzzy decision  theory” in the national level short term training programme sponsored by AICTE & ISTE held at Karunya Institute of technology, Coimbatore during May 1999.
  • Delivered lecture on the topic “Multichannel ECG pattern analysis using neural    networks” in the national level short-term training programme sponsored by AICTE & ISTE held at Karunya Institute of technology, Coimbatore during May 1999.

Sessions Chaired in the Conferences

  • Interview Panel Member for faculty recruitment in Ahalia School of Engineering & Technology, Palakkad on 9/5/2014
  • Chaired a session in the International Conference on Women in Computing (AICWIC 2013) between January 9 and 11, 2013 at Amrita Vishwa Vidya Peetham, Coimbatore
  • Chaired a session in the International conference on Machine Vision and Image Processing (MVIP12) organized by Department of Instrumentation and Control Systems Engineering, PSG College of Technology on December 14 & 15, 2012
  • Chaired a session in the National Conference on “Recent trends in Electronics and Communication Engineering” on 7.03.2012 at Ranganathan College of Engineering, Thondamuthur, Coimbatore - 641 109.
  • Chaired a session in the Regional Level Symoposium SNGPC Techmeet 2006 at Sree Narayanaguru Polyechnic College, Madukkarai, Coimbatore on 06.01.2006.

Reviewer

  • International Journal of Biomedical Engineering and Technology (IJBET) – Inderscience
  • International journal of medical imaging and heath informatics
  • IET Image Processing
  • VLSI-SATA 2015, ASE , Bangalore, program committee member and reviewer
  • International Conference on Computational Intelligence in Data Mining, Springer, ICCIDM-2014
  • International conference on power, signals, control and computations January 9-11, 2014, Vidya Academy of science & Technology, Thrissur, Kerala.
  • International conference on Machine Vision and Image processing (MVIP12)  organized by Department of Instrumentation and Control Systems Engineering, PSG College of Technology on December 14 & 15, 2012
  • National conference on “Recent Trends in Communication and Signal Processing”  (RTCSP 2010, RTCSP 2011, RTCSP 2013 and RTCSP 2014) at Amrita Vishwa Vidyapeetham, Coimbatore.
  • International Conference on “Communication Technology and System Design” ICCTSD 2011 and proceedings (Elsevier) at Amrita Vishwa Vidyapeetham

Other Assignments carried out apart from teaching in Amrita from 2001 -2015:

  • Guiding   Ph.D students in the area of  signal and image processing
  • Setting up of DSP hardware lab with Xilinx system generator and related hardware equipments. In connection with this training programs and workshops will be conducted each year. This will enable the students and researchers in executing projects like implementation of signal and image processing algorithms in hardware.
  • Class counselor (2000-2004 Batch), Class Advisor (2004-2008 Batch), Class Advisor and Year Coordinator (2010-2014 Batch)
  • Project coordinator (2008 and 2013)
  • Guided nearly 20 UG and PG projects
  • Digital Lab Incharge (2007-2012)
  • Contributed during NBA committee visit during 2003.
  • NAAC coordinator
  • Discipline committee member during Amritavarsham 2003 and food serving committee member during Amritavarsham 2013
  • Ph. D admission coordinator
  • Member of various committees during Institution day, convocation, Amritotsavam, Gokulashtami celebrations etc.,
  • Contributed in syllabus preparation for M.Tech VLSI Design (2002-2004 Batch), Electronics and Instrumentation Engineering (2004-2008 Batch), M. Tech Communication Engineering and Signal Processing (2014-2016 Batch), M.Tech Computer Vision and Image Processing, B. Tech (2014-2018), M.Tech Automative Electronics (2015-2017)
  • Significant contribution during the commencement of M.Tech VLSI Design in the year 2002 like developing the lab setup, coordinating the projects etc.,
  • Accompanied students to Amritapuri in the year 2010.
  • Accompanied students M. Tech VLSI students for industrial visits in the year 2004
  • Introduced new electives ‘Sparse Signal and Image Processing’ in the B. Tech   curriculum. ‘Image and Video Processing’ and ‘Hexagonal Image Processing’ in the  M. Tech curriculum.
  • Thrust Area Group (TAG) coordinator – Machine Intelligence Group

Publications

Publication Type: Journal Article

Year of Publication Title

2019

Abhishek S., S. Veni, and Narayanankutty, K. A., “Biorthogonal wavelet filters for compressed sensing ECG reconstruction”, Biomedical Signal Processing and Control, vol. 47, pp. 183-195, 2019.[Abstract]


This paper elaborates the design details of a new set of bi orthogonal wavelet filters derived from double sided exponential splines. The designed wavelets are applied in compressed sensing (CS) scenario and results were quite promising. CS is a signal acquisition paradigm, which surpasses the traditional limit of Nyquist sampling. Increasing the reconstruction quality with minimum number of samples in CS is always challenging. We have addressed this challenging task of increasing the reconstruction quality within a minimum number of measurements in CS by developing this new set of biorthogonal wavelet filters. Biorthogonal wavelets have several advantages such as linear phase as compared to orthogonal wavelets. This wavelet which we prefer to call as dew1 (double exponential wavelet 1) is applied in CS based ECG reconstruction scenarios and experimented over 21 data records from MIT arrhythmia data base. A total of 950 experiments were conducted in three CS based methodologies for ECG reconstruction and the results were noted. Over all we were able to get nearly 30% improvement in the reconstruction quality. This paper elaborates the design of these bi orthogonal filters and its application in CS based ECG reconstruction scenario. Other than endorsing the results, we also aim to familiarize this newly designed wavelet so it can be further experimented in different domains.

More »»

2018

E. Jose and S. Veni, “Vacant Parking Lot Information System Using Transfer Learning and IoT”, Journal of ICT Research and Applications, vol. 12, 2018.[Abstract]


Parking information systems have become very important, especially in metropolitan areas as they help to save time, effort and fuel when searching for parking. This paper offers a novel low-cost deep learning approach to easily implement vacancy detection at outdoor parking spaces with CCTV surveillance. The proposed method also addresses issues due to perspective distortion in CCTV images. The architecture consists of three classifiers for checking the availability of parking spaces. They were developed on the TensorFlow platform by re-training MobileNet (a pre-trained Convolutional Neural Network (CNN)) model using the transfer learning technique. A performance analysis showed 88% accuracy for vacancy detection. An end-to-end application model with Internet of Things (IoT) and an Android application is also presented. Users can interact with the cloud using their Android application to get real-time updates on parking space availability and the parking location. In the future, an autonomous car could use this system as a V2I (Vehicle to Infrastructure) application in deciding the nearest parking space.

More »»

2018

, Narayanankutty, K. A., S. Veni, and K. P. Soman, “Survey on Total Variation based Image Regularization Algorithms forImage Denoising”, International Journal of Pure and Applied Mathematics, vol. 118, pp. 3723-3730, 2018.

2018

S. Anant and S. Veni, “Safe Driving using Vision-based Hand Gesture Recognition System in Non-uniform Illumination Conditions”, Journal of ICT Research and Applications, vol. 12, pp. 154-167, 2018.[Abstract]


Nowadays, there is tremendous growth in in-car interfaces for driver safety and comfort, but controlling these devices while driving requires the driver’s attention. One of the solutions to reduce the number of glances at these interfaces is to design an advanced driver assistance system (ADAS). A vision-based touch-less hand gesture recognition system is proposed here for in-car human-machine interfaces (HMI). The performance of such systems is unreliable under ambient illumination conditions, which change during the course of the day. Thus, the main focus of this work was to design a system that is robust towards changing lighting conditions. For this purpose, a homomorphic filter with adaptive thresholding binarization is used. Also, gray-level edge-based segmentation ensures that it is generalized for users of different skin tones and background colors. This work was validated on selected gestures from the Cambridge Hand Gesture Database captured in five sets of non-uniform illumination conditions that closely resemble in-car illumination conditions, yielding an overall system accuracy of 91%, an average frame-by-frame accuracy of 81.38%, and a latency of 3.78 milliseconds. A prototype of the proposed system was implemented on a Raspberry Pi 3 interface together with an Android application, which demonstrated its suitability for non-critical in-car interfaces like infotainment systems

More »»

2018

E. K. Jose and S. Veni, “YOLO classification with multiple object tracking for vacant parking lot detection”, Journal of Advanced Research in Dynamical and Control Systems, vol. 10, pp. 683-689, 2018.[Abstract]


Advanced vacant lot detection systems are becoming an integral part of modern outdoor parking fields. As most of the parking fields are equipped with CCTV surveillance, vision-based solution has emerged as an effective, low-cost alternative. Although, image processing-based solutions suffer from issues due to irregular illumination, climatic variations, partial occlusion and perspective distortion due to camera placement, deep learning-based approaches have proved to be resilient. Another typical problem is the transient occlusion of the lots from the camera view due to passing-by vehicles and people. This paper presents a robust method for vacant lot detection by combining merits of deep learning approach with motion tracking to overcome the above issues. The fundamental idea is to find out a static frame which is free of any moving objects and submit it to a deep learning model for counting and localisation of vacant lots. Assuming smooth and streamlined motion of objects, motion tracking is implemented with constant velocity Kalman filter. Presence of motion is decided by checking alive-tracks in the current frame. Once a motion-free frame is recognised, the parking lot portion in the frame is cropped and input to a pre-trained YOLO (You Only Look Once) CNN (Convolutional Neural Network) model for counting and localisation of cars. Number of vacant lots are found by subtracting this count from the total number of available parking lots and their locations are determined by cross-matching detected bounding boxes of the cars against the pre-calculated locations of all the parking lots. © 2018, Institute of Advanced Scientific Research, Inc. All rights reserved.

More »»

2018

S. Anant and S. Veni, “Sensor-based Hand Gesture Control System for Safe Driving”, Journal of Advanced Research in Dynamical and Control Systems, vol. 10, pp. 690-698, 2018.[Abstract]


Nowadays, car’s functionalities are being improved by adding more and more in-car interfaces to increase driver’s safety and comfort. But at the same time it has lead to driver distraction due to complex human machine interaction (HMI) interfaces which is the major cause of road accidents. A sensor-based touch-less hand gesture control system is recommended in proposed work which can relatively easily control the functionalities of in-car interfaces and mobile phones under constrained lighting conditions. Gestures can be performed in front of an infrared object detector sensing unit placed near the driver’s seat. The microcontroller unit generates an associated command based on the sensor data which is sent to the Bluetooth module via UART communication. The command can be received by establishing the connection with the Bluetooth module which can be further used to control the functionalities of interfacing units. An android application is developed to receive the commands via Bluetooth and control the functionalities of music player accordingly. The prototype implementation of proposed work on LPC2148 gives 100 percent accuracy (based on experiments) and low latency for online hand gestures makes it suitable for real time implementation. © 2018, Institute of Advanced Scientific Research, Inc. All rights reserved.

More »»

2017

Abhishek S., S. Veni, and Narayanankutty, K. A., “Exponential-splines in compressed sensing ECG reconstruction”, International Journal of Pure and Applied Mathematics, vol. 114, pp. 299-310, 2017.[Abstract]


Use of Splines are not yet investigated for compressed sensing (CS). We tried exponential splines (1E-splines) and double sided exponential splines (2E-splines, proposed here) in compressed sensing scenario for ECG reconstruction and found that both outperform commonly used wavelets based approaches. Using these splines, peak root mean Square deviation (PRD) values were much lower for the same amount of measurements when compared to bi-orthogonal wavelets. The frequency domain representations of these 2E-Splines were also investigated.

More »»

2017

S. Veni, Priya, P. M. Vishnu, Mala, G. M. Aishwarya, Kayartaya, A., and Anusha, R., “Computer Aided System for Detection and Classification of Brinjal leaf Diseases using Thermal and Visible Light Images”, Journal of Theoretical and Applied Information Technology, vol. 95, pp. 5224-5236, 2017.[Abstract]


Agriculture plays a significant role in the overall socio-economic fabric of India. One of the several problems it faces in the country is the decline in productivity due to the drastic increase in plant diseases. The observations for detection of such diseases can be prohibitively expensive. Hence, a system which provides a faster and more accurate solution is necessary. Thermal images have a fine potential for early detection of diseases due to the temperature variations that occur as a result of the change in transpiration rate in plant leaves. Thus an attempt is made for the combined analysis of the visible light and thermal image features for early and accurate disease detection. The proposed work aims at developing a computer aided system that uses image processing algorithms to detect and classify plant diseases from Solanum Melongena (brinjal) leaves. The process starts with image acquisition using thermal and RGB cameras to obtain the data set, these images are then pre-processed and the region of interest is segmented out. The colour and temperature features are extracted and are used to detect and classify the healthy and diseased leaves. For classification, Support Vector Machine (SVM) and Artificial Neural Network (ANN) are used and their performances are compared. The experimentation reveals that SVM has a better accuracy (90.9%) than that of ANN (89.1%)

More »»

2017

S. Veni and Thushara, S., “Multimodal Approach to Emotion Recognition for Enhancing Human Machine Interaction - A Survey”, International Journal on Advanced Science, Engineering and Information Technology, vol. 7, pp. 1428-1433, 2017.[Abstract]


Emotions are defined as a mental state that occurs instinctively rather than through voluntary effort. They are strong feelings triggered by experiencing the joy, hate, fear, love and is followed by some physiological changes. Emotions play a vital role in social interactions and facilitate the decision making and perception in human being. Emotions are conveyed through speech, facial expression or by physiological signals. There are 6 emotions which are treated as universal emotions: anger, happiness, sadness, disgust, surprise and fear. This paper projects different emotion recognition systems which aim at enhancing the Human-Machine interaction. The techniques and systems used in emotion detection may vary depending on the features inspected. This paper explores them in a descriptive and comparative manner. Further the various applications that adopt these systems to reduce the difficulties in implementing the models in real-time are contemplated. Also, A multimodal system with both speech and facial features is proposed for emotion recognition through which it is possible to obtain an enhanced accuracy compare with the existing systems

More »»

2017

Kamalaveni V., S. Veni, and A., N. Kutty K., “Improved self-snake based anisotropic diffusion model for edge preserving image denoising using structure tensor”, Multimedia Tools and Applications, pp. 18815-18846, 2017.[Abstract]


The performance of classifier algorithms used for predictive analytics highly dependent on quality of training data. This requirement demands the need for noise free data or images. The existing partial differential equation based diffusion models can remove noise present in an image but lacking in preserving thin lines, fine details and sharp corners. The classifier algorithms can able to make correct judgement to which class the image belongs to only if all edges are preserved properly during denoising process. To satisfy this requirement the authors proposed a new improved partial differential equation based diffusion algorithm for edge preserving image denoising. The proposed new anisotropic diffusion algorithm is an extension of self-snake diffusion filter which estimates edge and gradient directions as eigenvectors of a structure tensor matrix. The unique feature of this proposed anisotropic diffusion algorithm is diffusion rate at various parts of an image matches with the speed of level set flow. In the proposed algorithm an efficient edge indicator function dependent on the trace of the structure tensor matrix is used. The proposed model performs best in preserving thin lines, sharp corners and fine details since diffusion happens only along edges and diffusion is totally stopped across edges in this model. The additional edge-stopping term which is a vector dot product of derivative of an edge stopping function and derivative of an image computed along gradient and edge orthogonal directions is used in this model as shock filter which enables increased sharpness at all discontinuities. The performance of proposed diffusion algorithm is compared with other classical diffusion filters like conventional perona-malik diffusion, conventional self-snake diffusion methods. © 2017 Springer Science+Business Media New York

More »»

2016

Abhishek S., S. Veni, and Narayanankutty, K. A., “Splines in Compressed Sensing”, International Journal on Advanced Science, Engineering and Information Technology, vol. 6, pp. 469–476, 2016.[Abstract]


It is well understood that in any data acquisition system reduction in the amount of data reduces the time and energy, but the major trade-off here is the quality of outcome normally, lesser the amount of data sensed, lower the quality. Compressed Sensing (CS) allows a solution, for sampling below the Nyquist rate. The challenging problem of increasing the reconstruction quality with less number of samples from an unprocessed data set is addressed here by the use of representative coordinate selected from different orders of splines. We have made a detailed comparison with 10 orthogonal and 6 biorthogonal wavelets with two sets of data from MIT Arrhythmia database and our results prove that the Spline coordinates work better than the wavelets. The generation of two new types of splines such as exponential and double exponential are also briefed here .We believe that this is one of the very first attempts made in Compressed Sensing based ECG reconstruction problems using raw data.

More »»

2016

K. Vanjigounder, A, N. K., and S. Veni, “Performance Comparison of Total Variation based Image Regularization Algorithms”, International Journal on Advanced Science, Engineering and Information Technology, vol. 6, no. 4, 2016.[Abstract]


The mathematical approach calculus of variation is commonly used to find an unknown function that minimizes or maximizes the functional. Retrieving the original image from the degraded one, such problems are called inverse problems. The most basic example for inverse problem is image denoising. Variational methods are formulated as optimization problems and provides a good solution to image denoising. Three such variational methods Tikhonov model, ROF model and Total Variation-L1 model for image denoising are studied and implemented. Performance of these variational algorithms are analyzed for different values of regularization parameter. It is found that small value of regularization parameter causes better noise removal whereas large value of regularization parameter preserves well sharp edges. The Euler’s Lagrangian equation corresponding to an energy functional used in variational methods is solved using gradient descent method and the resulting partial differential equation is solved using Euler’s forward finite difference method. The quality metrics are computed and the results are compared in this paper. More »»

2016

J. Sethupathy and S. Veni, “OpenCV based disease identification of mango leaves”, International Journal of Engineering and Technology, vol. 8, pp. 1990-1998, 2016.[Abstract]


This paper aims in classifying and identifying the diseases of mango leaves for Indian agriculture. K-means algorithm is chosen for the disease segmentation, and the disease classification and identification is carried out using the SVM classifier. Disease identification based on analysis of patches or discoloring of leaf will hold good for some of the plant diseases, but some other diseases which will deform the leaf shape cannot be identified based on the same method. In this case leaf shape based disease identification has to be performed. Based on this analysis two topics are addressed in this research paper. (1) Disease identification using the OpenCV libraries (2) Leaf shape based disease identification.

More »»

2016

Abhishek S., S. Veni, and Narayanankutty, K. A., “Improving information content in Compressed Sensing by modifying the random re-construction matrices”, Indian Journal of Science and Technology, vol. 9, 2016.[Abstract]


Background/Objectives: Compressed Sensing (CS) is an efficient sensing paradigm which guarantees reasonable reconstruction with less number of samples. We aim to increase the reconstruction quality of signals in CS. Methods/Statistical Analysis: The behavior of random matrices is analyzed and an efficient method for improving the reconstruction quality is developed in CS based ECG reconstruction applications. The method is compared against Biorthogonal wavelet based approaches. Findings: Our analysis reveals that introduction of a modified column vector in the reconstruction matrix, which contains the sum of all columns of random matrix increases the reconstruction quality in CS applications. This idea was applied to different sparsifying domains and the results are very encouraging. We studied the effect of doing this on the singular values and both unitary matrices U and V. The first singular value (σ) shot up making the condition number high, however there was not much change in the other singular values. The matrix U seems to remain random unitary matrix, where as matrix V has one value becoming unity in its rank space. Application/Improvements: Compared to wavelet based approaches the method shows reasonable improvement in Percentage Root Square Deviation (PRD).

More »»

2015

A. J. Thottupattu, Neha, S., and S. Veni, “Hardware software co-simulation of IIR filter using Xilinx system generator for FPGA implementation”, International Journal of Applied Engineering Research, vol. 10, pp. 37151-37155, 2015.[Abstract]


This paper proposes a method for implementing a Butterworth IIR low pass filter on Xilinx Spartan-6 XC6SLX45 FPGA board. The FPGA implementation is preferred because of increased computational speed compared with implementation in DSP processors. The IIR filter coefficients are calculated manually and the direct form II structure was simulated on Simulink with Xilinx block sets. In addition to simulation, hardware/software co-simulation was performed and it was observed that similar results were obtained. © Research India Publications.

More »»

2014

S. Veni, “Vision Based Hexagonal Image Processing”, Springer Journal - Signal, Image and Video Processing (SIViP), , vol. 8, no. 2, pp. 317-326, 2014.[Abstract]


About 97% receptive field of the neurons is very closely described as 2D Gabor wavelet and it is mostly suitable for vision system modeling [8]. Immense work is available on texture information, especially for rectangular structures [37- 40]. However, there is a little work in recognizing minute details in an image by either interpolation or enhancement. Hexagons have many advantages namely six fold symmetry, well behaved connectivity, improved angular resolution, storage savings, computational speed, and circular 7-pel shape. In the tessellations with Hexagons, if v is spatial domain lattice, then frequency domain lattice or reciprocal lattice v~ is obtained as v = 2π (v −1)T ). The basis vectors in the two domains are seen to be mutually orthogonal, which is due to the fact that the Fourier transform is an orthogonal projection. In the past years, there had been many attempts in representing hexagons in the regular square lattice or in a Spiral Addressing Scheme (SAS) [13-34]. Regular geometry is only kept in the case of SAS, however processing such pseudo lattices gave rise to better results compared with square lattices. This research work started with implementation of above mentioned hexagonal pseudo lattices and later entered on a real hexagonal lattice through the Hex - spline process described by D. Van De Ville et al. [45]. Hex-spline process is a structure where regular hexagon can be represented and it is basically used for interpolation. Filtering the images was attempted by Gabor kernels in hexagonal domain in different orientations, on this type of structure. As the orthogonal directions of the Gabor filter in the three directions ( 00, 600, 1200 ) are converged between three adjacent pixels, it was considered important to filter out the images in these directions. A low pass filter and high pass filter may be used to enhance surface information and edge information respectively. When the kernels are placed on image pixel locations and add, it is not only giving just image enhancement, but also facilitates interpolation. This is because, as the sigma values in a Gabor 23 filter reduce, the Gaussian envelope covers only a part of a wave of the modulating sinusoids, to render a low-pass characteristic to the filter. While the low-pass component is predominant, the edge enhancement part is still present in the three orthogonal directions as additional nonlinearity in the kernel.

More »»

2014

S. Veni and Narayanankutty, K. A., “Vision-based hexagonal image processing using Hex-Gabor”, Signal, Image and Video Processing, vol. 8, pp. 317–326, 2014.[Abstract]


About 97{%} receptive field of the neurons is very closely described as 2D Gabor wavelet and it is mostly suitable for vision system modeling. Immense work is available on texture information, especially for rectangular structures. However, there is a little work in recognizing minute details in an image on hexagonal structure by either interpolation or enhancement. In this work, the two important operations of biological visual system such as enhancement and interpolation are performed using the Hex-Gabor process. It is possible to obtain an error-free image at sigma = 2/pi using the proposed Hex-Gabor process and the significance of this sigma value is proved. For the performance analysis standard reflected images and X-ray images are considered. More »»

2014

S. Veni and Vinod, S., “Hardware Implementation of Hexagonal Sampling based Bio-Inspired Retinal Encoder”, International Journal on Signal and Imaging Systems Engineering, Inderscience (Scopus indexed), vol. 10, pp. 84-94, 2014.[Abstract]


This paper addresses hardware implementation of a power efficient retinal encoder system used in visual prosthesis equipment for blind people. The hardware architecture is inspired from the retinal receptive fields in mammalian vision system. The captured image is passed through several filter banks in different filtering stages in primate vision system. As the photoreceptors in the primate vision system are arranged in hexagonal fashion, the hexagonal tessellation scheme was found to be the most suitable sampling scheme for retinal image processing. In this work, the hardware implementation of different retinal filtering stages and final edge detection scheme is performed in Altera Cyclone II FPGA and in Synopsys Design Vision. An area efficient Cellular Logic Array Processing (CLAP) algorithm is used as the final stage edge detector. Both rectangular and hexagonal edge detection schemes were tested and their performance was analysed using Berkeley Segmentation Dataset and ROC performance scheme.

More »»

2014

L. Nagaraj, .Varshini, M., K.R, M., Sreenesh, B., .Sivakumar, V., and S. Veni, “Compressed sensing system for efficient ECG signal compression”, International Journal of Research in Engineering and Technology, vol. 3, no. 7, 2014.[Abstract]


Compressed sensing (CS) is a novel idea wherein a signal can be sampled at sub-Nyquist rates and still be effectively reconstructed. Many natural signals such as the ECG signal are sparse and have sparse representation when expressed in a suitable basis. Compressed sensing exploits the sparsity by acquiring a small number of projections on to random vectors which are sufficient to recover the signal. This theory enables an effective implementation of patient-centric telecardiology or mobile cardiology systems. It guarantees improvement in performance by drastically reducing the number of samples that requires to be either stored or transmitted. Specifically in the context of ECG monitoring systems, CS signal acquisition revolutionizes miniaturization of the hardware and improves its energy efficiency. This work proposes to create a Compressed sensing based mathematical framework for the acquisition and recovery of an ECG signal which has been further classified into normal and abnormal categories. During the compression stage, a sensing matrix which results in a low PRD (Percentage root mean square distortion) is used and an efficient reconstruction algorithm is employed to retrieve the most valuable information from the ECG signal. The classification of the ECG signal is done by studying the region of interest i.e. the QRS complex. The heart rate , the interval between two R peaks and the amplitude of the R peaks contributes chiefly to determining an abnormality in the ECG signal. This model can be implemented with a wireless body sensor network (WBSN) which may be used to alert a doctor in emergency situations. More »»

2013

S. Aiswarya and S. Veni, “Hardware Implementation of EZW based Image Compression with Huffman coding”, International Journal of Engineering Science and Innovative Technology (IJESIT), vol. 2, no. 5, pp. 437-445, 2013.[Abstract]


Embedded Zero-tree Wavelet (EZW) is a wavelet based image compression scheme. It is basically a quantization stage that incorporates some characteristics of the wavelet decomposition. The EZW approach and its descendants significantly outperform some of the generic approaches. The wavelet coefficients in different sub bands represent the same spatial location in the image. This is an important characteristic used by EZW. In case of decomposition, since the size of the different sub bands is different, then a single coefficient in the smaller sub band may represent the same spatial location as multiple coefficients in the other sub bands. This paper describes hardware implementation of EZW encoding algorithm along with Huffman encoding and decoding architectures. After performing lifting based DWT technique and EZW algorithm, Huffman coding ensures further compression of the image. In Huffman coding no bit string is a prefix of any other bit string. Hence each code is uniquely decodable.

More »»

2011

S. Veni and Narayanankutty, K. A., “Gabor Functions for Interpolation on Hexagonal Lattice”, International Journal of Electronics & Communication Technology (IJECT), vol. 2, no. 1, 2011.[Abstract]


An interpolation model using Gabor Filter is demonstrated on hexagonally sampled data, which outperform classical B-splines and MOMS. Our method has optimal approximation theoretic performances, for a good quality image. The computational cost is considerably low when compared to similar processing in the rectangular domain. In this paper the parameter sigma of 2/pi is found to satisfy most of the image interpolation requirements in terms of high Peak Signal-to-Noise Ratio (PSNR) , lower Mean Squared Error (MSE) and better image quality by adopting a windowing technique. More »»

2011

S. Veni, Narayanankutty, K. A., and A, F., “Employing Hexagonal Wavelets for Detecting Microcalcification in Digital Mammography”, ICGST International Journal on Graphics, Vision and Image Processing, GVIP, vol. 11, no. 1, pp. 59-66, 2011.[Abstract]


By combining the advantages of wavelets with the advantages of hexagonal grid, we get the hexagonal wavelets, which are of no doubt faster and efficient than the conventional wavelet. This work presents a wavelet transform on a hexagonal lattice, based upon the method of lifting scheme. The work uses a novel addressing scheme known as spiral addressing scheme which is symmetric, spatiotopic, and hierarchical for representing hexagonal images. As a case study the proposed wavelet was applied to digital mammography, where the utility was effectively demonstrated achieving similar results to the hexagonal wavelet used in

More »»

2011

S. Veni, .A.Narayanankutty, K., and Raffi, M., “Hardware Implementation of Edge detection on Hexagonal Sampled Image Grids”, International Journal of Computer Applications (0975 - 8887), vol. 24, 2011.[Abstract]


Increasing Processing capabilities of graphic devices and recent improvements in CCD technology have made hexagonal sampling attractive for practical applications. Also, hexagonal representation has special computational features that are pertinent to the vision process. This paper describes Edge detection operation on hexagonally sampled images and its hardware implementation based on Cellular Logic Array Processing (CLAP) algorithm. This architecture builds up a virtual hexagonal grid system on the memory space of computer and processing algorithms can be implemented on such virtual spiral space, thereby decreasing the computational complexity. These operations were done on hexagonal sampled grid using MATLAB version 7 and the results were compared with rectangular sampled grid. MODELSIM and Quartus II software were used for analysis and synthesis. The performance was tested using Altera Cyclone II FPGA. It was observed from the results that there is a marginal improvement while processing with hexagonal sampled grid. Hardware utilization is found to be less for the image sampled on hexagonal grid compared with rectangular grid. General Terms Image processing, Edge detection, VLSI architecture. Keywords Hexagonal image processing, CLAP algorithm, FPGA implementation of CLAP algorithm. More »»

2010

S. Veni and Narayanankutty, K. A., “Image Enhancement of Medical Images using Gabor Filter Bank on Hexagonal Sampled Grids”, World Academy of Science, Engineering and Technology, no. 65, pp. 816-821, 2010.[Abstract]


For about two decades scientists have been developing techniques for enhancing the quality of medical images using Fourier transform, DWT (Discrete wavelet transform),PDE model etc., Gabor wavelet on hexagonal sampled grid of the images is proposed in this work. This method has optimal approximation theoretic performances, for a good quality image. The computational cost is considerably low when compared to similar processing in the rectangular domain. As X-ray images contain light scattered pixels, instead of unique sigma, the parameter sigma of 0.5 to 3 is found to satisfy most of the image interpolation requirements in terms of high Peak Signal-to-Noise Ratio (PSNR), lower Mean Squared Error (MSE) and better image quality by adopting windowing technique.

More »»

2009

S. Veni, Narayanankutty, K. A., and Kirankumar, M., “Design of Architecture for Skeletonization on Hexagonal Sampled Image Grid”, International Journal on Graphics, Vision and Image Processing (ICGST-GVIP), vol. 9, no. 1, 2009.[Abstract]


ABSTRACT This paper describes skeletonization and reconstruction operation of binary image using synchronous processor array based on hexagonally sampled images . A modified architecture using the principle of Hilditch's algorithm was constructed using synchronous processing elements on hexagonal grid. Based on the architecture for rectangular skeletonization operations, an algorithm for reconstruction is designed, which is a new attempt. The processing elements connected in rectangular array and hexagonal array were investigated. Hexagonal reconstruction gave superior results, in terms of time and performance. For hardware implementations, we have used Modelsim for simulation, Quartus II Software for analysis and synthesis. The performance was tested using Altera Cyclone II FPGA. It was observed that hardware utilization is found to be less for the image sampled on hexagonal grid than on rectangular grid. More »»

2009

P. Vidya, S. Veni, and Narayanankutty, K. A., “Performance Analysis of Edge Detection Methods on Hexagonal Sampling Grid”, International Journal of Electronic Engineering Research, vol. 1, pp. 313–328, 2009.

Publication Type: Conference Paper

Year of Publication Title

2018

K. S. Kiran, Mandal, A., Kumar, K. R. Prasann, Mitra, P., and S. Veni, “A Comparative Study of Dictionary Learning Algorithms on Speech Recognition Task”, in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018.[Abstract]


In this paper, different dictionary learning and sparse coding algorithms are studied namely k-medoid, sparse non-negative matrix factorization (sNMF), active newton set algorithm (ASNA) and supervised non-negative matrix factorization (sup. NMF) for spoken word recognition task. The number of dictionary atoms per word class determined as 100 based on our proposed approach is empirically verified to be optimal considering tradeoff between accuracy and time of computation. The recognition task involved classification (matching) of sparsely coded word templates generated using learned dictionaries. A classification method based on the sum of non-zero weights of the coded representation is proposed for word recognition. The method does not require building class specific models making it apt for template based recognition. Moreover, it does not require signal recovery unlike most of the existing template based methods that performs matching on templates derived from recovered signal. The representation generated using magnitude short-term fourier transform (STFT) features, sNMF for dictionary learning and sup. NMF for sparse coding in conjunction with our proposed method of classification is found to exhibit an accuracy of 88.82% on clean speech, the highest among those studied. This outperformed the accuracy figures of the corresponding methods based on signal recovery such as signal-distortion-ratio. For noisy speech at different signal-to-noise ratio (SNR) levels, the combined dictionary comprising of separately trained speech and noise dictionaries provided the best recognition accuracy of 35.5% at zero dB SNR.

More »»

2018

S. Prabhakaran, S. Veni, and Kathavate, V., “Implementation of Robotic Vision to Perform Threaded Assembly”, in Proceedings of the 2018 IEEE International Conference on Communication and Signal Processing, ICCSP 2018, 2018, pp. 358-364.[Abstract]


In manufacturing of mechanical parts and assemblies, proper thread-engagement between a bolt and a nut is vital for the performance and reliability of the product. Typically, this is a precision work, requiring repetitive manual operations. In this paper, we explain how such assembly operations can be carried out by collaborative robots co-bots by monitoring the position and orientation of the nut and bolt using an image-sensor camera. The focus of our discussion is the assembly-operation of bolting of a nut by the grippers of a co-bot. Slips and misalignment, leading to wrong positioning of the nut and the bolt, are identified by capturing the images of the two components in real time using Microsoft Kinect camera-sensor. 3D Reconstruction of the image captured by the camera-sensor is carried out using the Kinect Fusion application. The reconstructed image is in the form of a polygonal mesh which is further converted to 3D Point Cloud data which is less sensitive to noise. Thereafter, the Point Cloud is segmented by dividing the entire scene into many clusters in order to distinguish the objects of the scene as grippers and nut and bolt. These clusters can be used for the training of the co-bot for the proposed operation. This method of extracting object-boundaries leading to recognition of objects is a vital operation in the field of robotic vision. We provide baseline description of various machine learning techniques that can be applied to realize proper assembly of a nut and a bolt.

More »»

2018

S. Reshma and S. Veni, “Comparative Analysis of Classification Techniques for Crop Classification using Airborne Hyperspectral Data”, in Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2017, 2018, vol. 2018-January, pp. 2272-2276.[Abstract]


Crop classification using high-dimensional and high-resolution data is a challenging task. Though a large number of classes can be obtained from the hyperspectral data, the 'curse of dimensionality' causes the classification accuracy to be less than the expected value. A minimum noise transform has been applied to the data in this work, to reduce dimensionality and improve classification accuracy. This paper compares the different methods of supervised and unsupervised classification for the identification of different crops in a field. The results showed that it is better to use supervised methods over unsupervised as they yield better classification accuracy and kappa coefficient.

More »»

2017

S. Reshma, S. Veni, and George, J. E., “Hyperspectral Crop Classification using Fusion of Spectral, Spatial Features and Vegetation Indices: Approach to the Big Data Challenge”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017.[Abstract]


The world keeps on generating massive amounts of data daily, which lead to the demands for finding new methods to deal with challenges related to `Big Data'. Automatic identification of crops is one of the major applications in the field of the hyperspectral image processing. The major curbs involved in crop classification are: i) Huge dimension of the data and ii) Spectral Similarity amongst crops. This paper proposes a new method of crop classification in which fusion of spectral, spatial and vegetation indices is used as the feature set to overcome the limitation of spectral similarity problem. Here the processing is done in two stages: dimensionality reduction and supervised classification. The dimensionality reduction is done using Principal Component Analysis (PCA) and Minimum Noise Transform (MNF) technique and the selected dimensions are classified using Support Vector Machine Classifier. The results obtained using the proposed technique show that on integrating the vegetation indices along with the spectral and spatial features have raised the accuracy to 98.0749% and helped achieve a kappa coefficient of 0.9769.

More »»

2017

J. E. George, Aravinth J., and S. Veni, “Detection of Pollution Content in an Urban Area Using Landsat 8 Data”, in 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2017.[Abstract]


Pollution control is a challenging task in current scenario. The very first step to control pollution is to detect the sources of pollution. The urban areas are more polluted than rural due to the high population density. The pollutants considered in this paper are aerosol and asbestos sheets. The source of asbestos are building roofs which are mainly in urban area and that of aerosol is combustion of coal. The conventional image processing techniques failed to detect the pollutant in urban environment which can be performed well using multispectral imaging. Since each object has different temperatures using the TIR (Thermal Infrared) bands of Landsat 8 data, the urban objects are classified using the land surface temperature map. The presence of asbestos sheets is detected by change in intensity of images with respect to Band 7 (Short Wave Infrared) and Band 9 (Cirrus). Aerosol is comprised of components that cause air pollution. In this work, the PM10 value is considered as one of the measures to identify the concentration of particulate matters in specific area.

More »»

2016

K. A. Das, George, K. K., Dr. Santhosh Kumar C., S. Veni, and Panda, A., “Modified gammatone frequency cepstral coefficients to improve spoofing detection”, in 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2016.[Abstract]


Voice spoofing is one of the major challenges that needs to be addressed in the development of robust speaker verification (SV) systems. Therefore, it is necessary to develop systems (spoofing detectors) that are able distinguish between genuine and spoofed speech utterances. In this work, we propose the use of modified gammatone frequency cepstral coefficients (MGFCC) on enhancing the performance of spoofing detection. We also compare the effectiveness of GMM based spoofing detectors developed using mel frequency cepstral coefficients (MFCC), gammatone frequency cepstral coefficients (GFCC), modified group delay cepstral coefficients (MGDCC) and cosine normalized phase cepstral coefficients (CNPCC) with that of MGFCC. The experimental results on ASV spoof 2015 database show that MGFCC outperforms magnitude based, MFCC and GFCC, and phase based, MGDCC and CNPCC, features on the known attack conditions. Further, we performed a score level fusion of the systems developed using MFCC, MGFCC, MGDCC and CNPCC. It is observed that the fused system significantly outperforms all the individual systems for known and unknown attack conditions of ASV spoof 2015 database.

More »»

2016

S. Thushara and S. Veni, “A multimodal emotion recognition system from video”, in 2016 International Conference on Circuit, Power and Computing Technologies (ICCPCT), 2016.[Abstract]


Emotion recognition (ER) systems finds applications in many fields like call centres, humanoid Roberts and robotic pets, telecommunication, psychiatry, behavioral science, educational softwares, etc., In this work, the speech and facial features extracted from the video data is explored to recognize the emotions. Since both these features are compliment to each other, on combining them will result in higher performance. The features used for emotion recognition from video data are geometric and appearance based while prosodic and spectral features are employed for speech signal. Support Vector Machine (SVM) classifier is used to capture the emotion specific information. The basic aim of this work is to explore the capability of speech and facial features to provide the emotion specific information. More »»

2011

S. S. Murugan, Natarajan, V., S. Veni, and Balagayathri, K., “Analysis of adaptive algorithms to improve the SNR of the acoustic signal affected due to wind driven ambient noise in shallow water”, in 2011 International Symposium on Ocean Electronics, 2011.[Abstract]


Underwater signal transmission is a challenging task since the usable frequency range is limited to low frequency and the transmission of electromagnetic waves is impossible due to its high attenuation nature. Hence low frequency acoustic signal is more suited for transmission in underwater. Underwater transmission is highly affected by wind noise which is predominant at low frequency. The real time data collected from Indian Seas at Chennai (Bay of Bengal) are studied in detail using Welch, Bartlett and Blackman estimation methods and the results shows the effect of wind over 0-8 kHz range. Various adaptive algorithms are analyzed in detail and the Signal to Noise Ratio (SNR) values are tabulated for different wind speeds. The results shows that Recursive Mean Square (RLS) works better when compared to others. The maximum Signal to Noise Ratio (SNR) of about 42-51 dB is achieved. More »»

2011

S. Veni, S. Murugan, S., and Radha, S., “Adaptive algorithm for detection of underwater acoustic signals against ambient noise in shallow water at Indian seas”, in 2011 International Conference on Emerging Trends in Electrical and Computer Technology, 2011.[Abstract]


Effective underwater communication can be carried out when the masking effect of underwater ambient noise is reduced. The main objective of this paper is to develop an optimum adaptive algorithm for accurate detection of the underwater acoustic signal buried due to the effect of ambient noises in the near and far seas. A comparative analysis on various algorithms using MATLAB is performed and to validate its performance the signal to noise ratio is calculated. For this analysis the data collected using passive Sonar at Chennai at a depth of 5metre in shallow water region is considered. More »»

2011

S. Veni, Murugan, S. S., and Natarajan, V., “Modified LMS adaptive algorithm for detection of underwater acoustic signals against ambient noise in shallow water of Indian sea”, in 2011 International Conference on Recent Trends in Information Technology (ICRTIT), 2011.[Abstract]


In the underwater communication, the biggest challenge is to reduce the masking effect of underwater ambient noise. The main objective of this paper is to develop an optimum modified LMS adaptive algorithm for accurate detection of underwater acoustic signal, which is prone to the effect of ambient noise in the near and far seas. Comparative analyses on various algorithms are performed. This modified LMS algorithm is found better than the other existing algorithms with respect to the Signal to Noise Ratio (SNR) and Mean Square Error (MSE). For this analysis, data collected using passive Sonar at a depth of 5 meters in shallow water region. More »»

2009

S. L. Reddy, Vidya, P., S. Veni, and Narayanankutty, K. A., “Wavelet Based Edge Detection and Multiresolution Analysis on Hexagonal Sampled Grid using Interpolation”, in International conference on Signal and Image Processing (ICSIP 2009), Vidya Vikas Institute of Engineering & Technology, Mysore, 2009.

2008

S. Veni and A, F., “A Novel Hexagonal wavelet transform”, in Recent Trends in Computational Science" (ICRTCS - 2008), Toc H Institute of Science, Ernakulam, 2008.

2004

S. Veni and Dr. Yamuna B., “Analog VLSI implementation of Cellular Neural Network and its applications to Image Processing”, in International Conference on Systemics, Cybernatics and Informatics, Pentagram Research Centre Pvt Ltd, Hyderabad , 2004.

2003

S. Veni and Madhavan, B. K., “CMOS VLSI implementation of Analog neuron using PWM technique”, in National Conference on Emerging Trends in VLSI Design and Testing, PSG College of Technology, Coimbatore , 2003.

2002

S. Veni, “Color Image compression for Limited Displays using self organising feature map”, in National workshop on Computer vision, Graphics and Image processing, Thiagarajar College of Engineering, Madurai, 2002.

2001

S. Veni, “Cell locating strategy in Personal Communication Network”, in National Conference of Advanced Computing , PSG College of Technology, Coimbatore, 2001.

2001

S. Veni, “Personal Domain Applications using WAP”, in National conference on Emerging Trends in Engineering Design Automation, MNM Jain Engineering College, Chennai, 2001.

Publication Type: Conference Proceedings

Year of Publication Title

2018

P. Krithika and S. Veni, “Leaf Disease Detection on Cucumber Leaves using Multiclass Support Vector Machine”, Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2017, vol. 2018-January. Institute of Electrical and Electronics Engineers Inc., pp. 1276-1281, 2018.[Abstract]


In India, smart organic farming is gaining importance. There may be problems due to environment, temperature, humidity or nutrient deficiency in this farming. If we have a monitoring system for this farming it is possible to produce healthy plant. The aim is to address this issue using computer aided image processing technique. Main solution is to create an automation system which can detect the disease present in the leaf of the plant. In this paper, a first level attempt is made to detect diseases present in the leaf of salad cucumber. The most common diseases which are present in salad cucumber are Alternaria leaf blight, Bacterial wilt, Cucumber green mottle mosaic, Leaf Miner, Leaf spot, Cucumber Mosaic Virus (CMV) disease and so on. K-means clustering, an unsupervised algorithm along with Support Vector Machine(SVM) is used in this work to address this problem.

More »»

2017

R. Anand, S. Veni, and Aravinth J., “Big Data Challenges in Airborne Hyperspectral Image for Urban Landuse Classification”, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). pp. 1808-1814, 2017.[Abstract]


In recent years, it was a difficult task to classify a huge set of data due to the increasing population in urban places. As of now, satellite hyperspectral image provides information but this is not sufficient to classify data in urban areas. To develop the urban areas, accurate and timely information is necessary for the government. Hence, airborne hyperspectral data provides sufficient information for urban planning and disaster management. This paper, focuses on the following objectives: (i) To improve the classification accuracy in bigdata images (ii) To reduce the mixed pixels in residential buildings that are surrounded by small trees (iii) To bring down similar pixels of roads and parking lots. In this paper, 15 different classes were classified which are important for the growth in urban areas. The SVM classifier has more accuracy and better kappa coefficient compared with Neural Network (NN) and K-Means clustering. The Overall Accuracy (OA) has improved by 23.3.

More »»

2016

Anand R, S. Veni, and Aravinth J., “An Application of image processing techniques for Detection of Diseases on Brinjal Leaves Using K-Means Clustering Method(2016)”, Fifth International Conference on Recent Trends in Information Technology 2016 (ICRTIT 2016). Anna University, Chennai campus , 2016.

2016

T. Selvi P, P, V., R, J., Srikumar, S., and S. Veni, “Emotion Recognition from Videos Using Facial Expressions”, International Conference on Artificial Intelligence and Evolutionary Computations in Engineering Systems (ICAIECES-2016) . SRM University, 2016.[Abstract]


In recent days, automatic emotion detection is a field of interest and is used in fields such as e-learning, robotic applications, human–computer interaction (HCI), surveillance, ATM monitoring, mood-based playlists/YouTube videos, psychological studies, medical fields like supporting blind and dumb people, for treating autism in children, entertainment, animation, etc., The proposed work describes detection of human emotions from a real-time video or image with the help of classification technique. The major part of human communication constitutes of facial expression, which is around 55% of the total communicated information. The basic facial expressions that are considered by the psychologists are: happiness, sadness, anger, fear, surprise, disgust, and neutral. The proposed work aims to classify a given video into one of the above emotions using efficient facial features extraction techniques and SVM classifier. The author’s contribution is to increase the efficiency in emotion recognition by implementing the above mentioned superior feature extraction and classification methods.

More »»

2016

S. Abhishek, S. Veni, and Narayanankutty, K. A., “Exponential-Splines in Compressed Sensing ECG Reconstruction”, International Conference on Artificial Intelligence and Evolutionary Computations in Engineering Systems (ICAIECES-2016) . SRM University, 2016.

2016

R. Anand, S. Veni, and Aravinth J., “An Application of image processing techniques for Detection of Diseases on Brinjal Leaves Using K-Means Clustering Method”, IEEE International Conference on Circuit, Power and Computing Technologies”, ICCPCT. 2016.

2015

K. Ka George, Dr. Santhosh Kumar C., Panda, Ab, Raji Ramachandran, Das, K. Aa, and S. Veni, “Minimizing the false alarm probability of speaker verification systems for mimicked speech”, 2015 International Conference on Computing and Network Communications, CoCoNet 2015. Institute of Electrical and Electronics Engineers Inc., pp. 703-709, 2015.[Abstract]


Speaker verification (SV) systems need to be robust to mimicked voices of target speakers as non-target trials to make them usable in critical applications. However, the performance of SV systems for mimicked voice test conditions has not been extensively explored.

More »»

2015

Abhishek S., S. Veni, and Narayanankutty, K. A., “A trick to improve PRD during compressed sensing ECG reconstruction”, Second International Conference on Signal Processing and Integrated Networks (SPIN), 2015 2nd International Conference on. IEEE, Amity University, Noida, pp. 9-15, 2015.[Abstract]


In the problem of compressed sensing (CS) successful reconstruction can be achieved by maintaining a low mutual coherence between the columns in the vector space. In this work, a way to increase the mutual incoherence is introduced. This is achieved by replacing certain matrix domain of the sparse random matrix, which is used as the measurement matrix with null space bases. For convenience, this can be replaced even by identity matrices. The result shows that there is a substantial improvement in Peak Root mean Square deviation (PRD). Many different alternatives have been tried out and relative PRD were plotted. Thresholding is generally adapted in CS in order to reduce the PRD values. It was found that without using thresholding technique, it is possible to obtain reduction in PRD values. The time algorithmic performance was also analyzed and found to be better.

More »»

2014

S. Veni and Sarika, K., “Hardware Implementation of Hough Transform for Circle Detection ”, International Conference on Interdisciplinary Advances in Applied Computing (ICONIAAC ’14) . Proceedings of ACM , Amrita School of Engineering, Coimbatore , 2014.[Abstract]


Hough transform is a feature extraction technique used in image analysis, digital image processing and computer vision. To extract features from digital images, it is useful to be able to find arbitrary shapes like straight lines, circles, ellipses etc in the images. In order to achieve this goal, one must be able to detect a group of pixels that are on a required curve. Most of the elements are geometrically circular in shape and detecting circular shapes is an important task in image processing which is a preprocessing step before image analysis. Detection of circles using Hough Transform is most useful technique in the applications like iris detection, satellite imaginary, medical image processing, satellite imaging, Hyper spectral image processing etc., Hardware implementation of the Circular Hough Transform (CHT) is essential for real time applications. In this paper, the Hardware implementation of CHT using CORDIC algorithm is proposed which has not been addressed yet. The CORDIC algorithm reduces computational complexity by replacing exhaustive arithmetic operations with adders and shifters which is evident from the results obtained from this work.

More »»

2013

S. Veni, Jyothirmayie, P., G. Reddy, O., Vineela, G., Praveenkumar, S., and Srihrsha, V. L. V., “Lane Detection and Departure Warning System”, International Conference on Recent Trends in Engineering and Technology & Mechanics, Simulation and Control (ICRTET 2013) . pp. pp. 125-130, 2013.

2006

S. Veni, Narayanankutty, K. A., and Senthilnayaki, M., “Hexagonal Pixel Grid Modeling for Edge Detection and Design of Cellular Architecture for Binary Image Skeletonization”, INDICON 2006. India Conference, 2006 Annual IEEE, AMALTAS, India Habitat Centre, New Delhi, 2006.[Abstract]


Digital images can be represented by rectangular pixel grid model. Yet an alternate model paradigm using a hexagonal pixel grid can be used to discretize and process images which are more suitable for computer vision modeling. The merits of using hexagonal lattice are superior symmetry, definite neighborhood and fewer samples are needed compared to a rectangular lattice. This paper elucidates the sub sampling procedure needed to obtain the hexagonally sampled image from the conventional rectangularly sampled image. Two image processing operations namely edge detection and image skeletonization were done on hexagonal lattice and also rectangular lattice for comparison. The algorithm used for the edge detection of sub sampled images is based on CLAP (cellular logic array processor) algorithm. Image Skeletonization was done using iterative thinning method which is better suited for VLSI Implementation. The paper further deals with the design and implementation of a cellular processor array (CPA) that executes binary image skeletonization on a hexagonal lattice. The implementation shows better results compared to the existing methods

More »»

2005

S. Veni, George, R. Annie, and Kutty, K. A. Narayanan, “Boundary Contour System for Dynamic compression and Image Edge Enhancement”, INDICON, 2005 Annual IEEE. IEEE, IIT Madras, Chennai , pp. 457-462 , 2005.[Abstract]


Catalog No. 05EX1212 and Library congress catalog No. 2005932645

More »»

2005

S. Veni and Dr. Yamuna B., “Hardware implementation of CNN”, International Conference on Intelligent sensing and information Processing (ICISIP). IEEE , Le Royal Meridian, Chennai, pp. 320-325, 2005.[Abstract]


The requisite properties of analog CNN components, like the Gilbert multiplier, Operational transconductance amplifier, and the current mirror, were separately estimated. Interconnect for a single cell was analyzed , and extended for a 3 /spl times/3 CNN, that has been implemented. A programmable integration time-constant and a template programmability is found possible. It is also seen that implementation is possible at very low power levels, typically 124 uW. The network considered in this design is a continuous-time rectangular type CNN with r = 1. In this paper the network was implemented using analog VLSI techniques and their performance was verified using cadence spectre IC5. The designed CNN could be used for the applications such as image processing, solution of partial differential equation, modelling of nonlinear phenomenon, physical system simulation, etc.

More »»