Qualification: 
M.Tech
r_karthika[at]cb[dot]amrita[dot]edu

R. Karthika is working as an Assistant Professor in the department of Electonics and Communication Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore. She completed her B. E. degree in Electronics and Communication from Madras University in 2000. She received her M.Tech. degree in Computer Vision and Image Processing from Amrita Vishwa Vidyapeetham. Currently she is pursuing Ph. D. in Amrita Vishwa Vidyapeetham. Her current research interests include Pattern Recognition, Image Processing and Deep Learning. She is a member in Institution of Electronics and Telecommunication Engineers (IETE).

Education

  • Pursuing: Ph. D. in Image Processing
    Amrita Vishwa Vidyapeetham
  • 2011: M. Tech. in Computer Vision and Image Processing
    Amrita Vishwa Vidyapeetham

Professional Experience

Year Affiliation
2007- Till date Assistant Professor (SR), Amrita Vishwa Vidyapeetham
Domain : Teaching and Research
2001-2007(1.10.2017) Assistant Professor, Amrita Vishwa Vidyapeetham
Domain : Teaching and Research

Academic Responsibilities

SNo Position Class / Batch
1. Batch Coordinator 2016-2020
2. Class Adviser 2016-2020

Undergraduate Courses Handled

  1. Digital Signal Processing
  2. Signals and Systems
  3. Digital circuits and systems
  4. Microcontroller and its Applications

Post-Graduate / PhD Courses Handled

  1. Image and video processing (CSP)
  2. Sensing for autonomous vehicle

Innovations in Teaching - Learning

Innovation Method Description with Tools used
Common online continuous Assessment system is introduced in the subject 15 ECE202- Digital circuits and systems for 10 classes AUMS

Participation in Faculty Development / STTP / Workshops /Conferences

SNo Title Organization Period Outcome
1 National workshop on computer vision and image processing techniques Amrita vishwavidyapeetham, coimbatore April 30 - 31, 2017  
1. ISRO sponsored national seminar on Techniques and applications of hyperspectral image analysis. Amrita vishwavidyapeetham, coimbatore April 19 - 20, 2016 Elective Course and Research
2. ITAA-Training Amrita vishwavidyapeetham, coimbatore July 10, 2015  Trained for Counselling
3. DRDO sponsored National symposium on green Electronics Amrita vishwavidyapeetham, coimbatore December 12 - 13, 2014 Teaching learning process
4. Probability and graphical models Amrita vishwavidyapeetham, Coimbatore December 27 - 29, 2014 Research
5 IETE sponsored the art of technical paper writing and professional Ethics Amrita vishwavidyapeetham, Coimbatore October 16, 2014 Research
6. Research seminar on emerging perspectives in Nano electronics R&D Amrita vishwavidyapeetham, Coimbatore September 19, 2014 Research
7 Signal and image processing applications using Xilinx system generator Amrita vishwavidyapeetham, Coimbatore April 10 - 11, 2014 Research
8 ISTE workshop on signals and systems Indian institute of technologykharagpur January 2 - 12, 2014 Teaching learning process
9 Image processing with Beagle board Amrita vishwavidyapeetham, Coimbatore December 20, 2014 Research
10. National level workshop on Sparse image and signal processing Amrita vishwavidyapeetham, Coimbatore June 3 - 4, 2013 Research
11 Workshop on open source for computer vision and image processing Amrita vishwavidyapeetham, Coimbatore September 29 - October 12, 2011 Research
12 Facebook apps workshop on open sorce community Amrita vishwavidyapeetham, Coimbatore February 10, 2011 Learning
13 Ethical hacking workshop Amrita vishwavidyapeetham, Coimbatore February 11 - 12, 2011 Learning 
14 IETE sponsored faculty development programme on signals and systems Amrita vishwavidyapeetham, Coimbatore June 29 to July 3, 2009 Teaching learning process
15 workshop on support vector machines and applications Amrita vishwavidyapeetham, Coimbatore May 11 - 13, 2009 Research
16 Workshop on image processing techniques Amrita vishwavidyapeetham, Coimbatore January 5 - 7, 2009 Research
17 IETE workshop on Image processing algorithms Amrita vishwavidyapeetham, Coimbatore December 17 - 19, 2007 Research
18 LABVIEW 7.0 basics Amrita vishwavidyapeetham, Coimbatore February 7 - 19, 2005 Learning 
19 AICTE-ISTE sponsored short term training programme on self intelligent electro mechanical systems Kumaraguru college of technology March 15 - 26, 2004 Learning 
20 AICTE-ISTE sponsored short term training programme on  Introduction to bioinformatics algorithms and their parallel implementation Amrita vishwavidyapeetham, Coimbatore November 10 - 21, 2003 Learning 
         

Academic Research – PG Projects

SNo Name of the Scholar Programme Specialization Duration Status
1. Amara dineshkumer  Automotive Electronics Advanced driver assistance systems 2018-19 Ongoing
2. Bini alias Communication engineering and signal processing Remote sensing image classification using deep learning 2017-18  Completed
3 S.Sathya Computer vision and image processing Image processing 2016-17 Completed
4 Vishnumaya Computer vision and image processing Image processing 2015-16 Completed

Instructional Materials Developed

Name & Description Outcome
Instruction material for ECE 292-Digital signal processing lab Course for 2014 Curriculum Uniform course delivery for all the classes.

Publications

Publication Type: Journal Article

Year of Publication Title

2018

R. Karthika, BiniAlias,, and LathaParameswaran, “Content Based Image Retrieval of Remote Sensing Images using Deep Learning with Distance measures”, Journal of Advanced Research in Dynamical and Control System, vol. 10, no. 3, pp. 664-674, 2018.[Abstract]


The use of Convolutional neural networks (CNN) with deep learning performed an excellent performance in many applications of image processing. The use of CNN based techniques to extract image features from the final layer and the use of a single CNN structure may be used for identifying similar images. Learning feature extraction and effective similarity comparison comprises the Content-Based Image Retrieval (CBIR). In CBIR feature extraction, as well as similarity measures, play a vital role. The experiments are carried out in two datasets such as UC Merced Land Use Dataset and SceneSat Dataset. By using a pre-trained model that is trained on millions of images and is fine-tuned for the retrieval task. Pre-trained CNN models are used for generating feature descriptors of images for the retrieval process. This method deals with the feature extraction from the two fully connected layers, which is present in the VGG-16 network by using transfer learning and retrieval of feature vectors using various similarity measures. The proposed architecture demonstrates an outstanding performance in extracting the features as well as learning features without a prior knowledge about the images. By using various performance metrics, the results are evaluated and performance comparison was done. Cosine Similarity and Euclidean Distance performs better in both Fully connected layers.

More »»

2018

A. Dinesh Kumar and Karthika, R., “Novel Deep Learning Model for Traffic Sign Detection Using Capsule Networks”, CoRR, vol. abs/1805.04424, 2018.[Abstract]


Convolutional neural networks are the most widely used deep learning algorithms for traffic signal classification till date but they fail to capture pose, view, orientation of the images because of the intrinsic inability of max pooling layer. This paper proposes a novel method for Traffic sign detection using deep learning architecture called capsule networks that achieves outstanding performance on the German traffic sign dataset. Capsule network consists of capsules which are a group of neurons representing the instantiating parameters

More »»

2018

R. Karthika and Parameswaran, L., “An Automated Vision-based Algorithm for Out of Context Detection in Images”, International Journal of Signal and Imaging Systems Engineering, vol. 11, pp. 1-8, 2018.[Abstract]


Vehicular traffic on highways is a major concern relating to safety and security. Violation of traffic rules results in fatal incidents to a very large extent. In this work, an attempt has been made to detect violation of traffic rules namely vehicles in no parking and no stopping zones. Dataset consisting of cars in these zones has been used for experimentation. The proposed algorithm used histograms of oriented gradient (HOG) and Adaboost cascaded classifier for training. The traffic signs have been identified using Hough transform, Circlet transform and colour analysis. Experimental results are promising with an accuracy in the range of 90–97% with recognising no parking and no stopping sign

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2016

R. Karthika, Dr. Latha Parameswaran, B.K., P., and L.P., S., “Study of Gabor wavelet for face recognition invariant to pose and orientation”, Proceedings of the International Conference on Soft Computing Systems, Advances in Intelligent Systems and Computing, vol. 397. Springer Verlag, pp. 501-509, 2016.[Abstract]


Gabor filters have achieved enormous success in texture analysis, feature extraction, segmentation, iris and face recognition. Face recognition is one of the most popular biometric modalities which has wide range of applications in biometric authentication. The most useful property of a Gabor filter is that it can achieve multi-resolution and multi-orientation analysis of an image. This paper presents an algorithm using Gabor wavelets in capturing discriminatory content, obtained by convolving a face image with coefficients of Gabor filter with different orientations and scales. Support vector machine (SVM) has been used to construct a robust classifier. This method has been tested with publicly available ORL dataset. This algorithm has been tested, cross-validated and the detailed results are presented. It is inferred that the proposed method offers a recognition rate (94%) with tenfold cross-validation. © Springer India 2016.

More »»

2014

A. .S, .M, J., Prakash, K., .R, S., and Karthika, R., “Detection Of Vehicles Using Image Descriptor”, Proceedings of SARC-ITR International Conference. pp. 44-48, 2014.

2014

S. M. Priya and Karthika, R., “Unsupervised Environmental Sound Recognition”, Proceedings of International Conference on Embedded Systems(ICES 2014). pp. 44-48, 2014.

2012

R. Karthika, ,, and PVS, M., “Global Portfolio Optimization for BSE Sensex using the Enhanced Black Litterman Model”, International Conference on Modeling Optimization Computing, Technology, vol. 38. pp. 2987-2997, 2012.[Abstract]


The Markowitz mean-variance optimization algorithm, in conjunction with the enhanced Black Litterman model for estimating expected return of asset returns of Bombay Stock Exchange (BSE), is developed to solve the asset allocation problem. The estimation of expected rate of returns of assets is done by combining economical analysis and technical analysis. The former is done by economists to predict the rate of return based on the present growth of the company and various economic factors while the latter uses past historical data to predict the rate of return. This paper deals with the issues in the prediction of expected rate of return by using the Black Litterman Model which combines both public and private views. The problems of the original Black Litterman Model are analyzed, and the Black Litterman model is enhanced by including the error estimates resulting from the bootstrapping methods. The resulting predicted expected rate of the return vector is given as the input to the Markowitz Mean variance portfolio optimizer to get the better asset allocation model. Bombay Stock Exchange (BSE Sensex) dataset is used and the algorithm is implemented using MATLAB.

More »»

2012

R. Karthika, ,, Meghana, P. V. S., D, S., and , “Predicting BSE Sensex: Using Enhanced Black Litterman Model”, Fourth International Conference on Electronics Computer Technology, vol. 3. pp. 238-241, 2012.

2009

A. S, B, V., K, S., Krishnan, S., P, S., Karthika, R., and Sabarish Narayanan B., “Design of Planar Multi Layered Dielectric Structures using Binomial Matching Technique”, ELECTRON - Technical Report of Department of ECE, Special Issue, Proceedings of First National Conference on Recent Trends in Communication and Signal Processing (RTCSP’09), vol. 1. pp. 71-77, 2009.

2008

A. S, K, S., Krishnan, S., P, S., B, V., Sabarish Narayanan B., and Karthika, R., “Analysis and Performance of Planar Multi Layered Electromagnetic Absorbers for Shielding Applications”, National Symposium on Instrumentation (NSI 33). Vishakhapatnam, pp. 35-36, 2008.

Publication Type: Conference Paper

Year of Publication Title

2014

S. P. Mohanapriya, Sumesh, E. P., and Karthika, R., “Environmental sound recognition using Gaussian mixture model and neural network classifier”, in International Conference on Green Computing Communication and Electrical Engineering (ICGCCEE), 2014.[Abstract]


Environmental sound recognition is an audio scene identification process in which a person's location is found by analyzing the background sound. This paper deals with the prototype modeling for environmental sound recognition. Sound recognition involves the collection of audio data, extraction of important features, clustering of similar features and their classification. The Mel frequency cepstrum co-efficients are extracted. These features are used for clustering by a Gaussian mixture model which is a probabilistic model. Neural Network classifier is used for classification of the features and to identify the environmental audio scene. The implementation is done with the help of MATLAB. Five major environmental sounds which include the sound of car, office, restaurant, street, subway are considered. This shows a better efficiency than the already existing method. The efficiency achieved in this method is 98.9%. More »»