Qualification: 
Ph.D, M.Tech
tripty_singh@blr.amrita.edu

Dr. Tripty Singh currently serves as Assistant Professor at the department of Computer Science, Amrita School of Engineering, Bengaluru. She completed her Ph.D studies from Rajiv Gandhi Proudyogiki Vishwavidyalaya, Bhopal.

Publications

Publication Type: Journal Article

Year of Publication Title

2021

R. R. Nair and Dr. Tripty Singh, “MAMIF: multimodal adaptive medical image fusion based on B-spline registration and non-subsampled shearlet transform”, Multimedia Tools and Applications, pp. 1–27, 2021.[Abstract]


Off late, medical image fusion has emerged as an inspiring approach in merging different modalities of medical images. The fused image helps the medicos to diagnose various critical diseases quickly and precisely. This paper proposes two fusion algorithim named Multimodal Adaptive Medical Image Fusion (MAMIF) and Multimodal without Denoised Medical Image Fusion (MDMIF) and both of the method uses Non-Subsampled Shearlet Transform (NSST) and B-spline registration model. However as MAMIF uses denoise method, it provides better visually enhanced images. The presented MAMIF algorithim fuses the images without losing any vital information for the given set of real-time and public datasets. The entire fusion framework uses features extracted from NSST decomposed images by using Human Visual System (HVS) based Low Frequency (LF) sub-band fusion and Log-Gabor energy-based High Frequency (HF) sub-band fusion. The proposed framework is agnostic of source image size (pairs should be of the same size). The experiments were carried out leveraging 14 sets of image dataset that includes grayscale and color images. The performance calculation of the proposed MAMIF is evaluated based on the dataset collected from HCG hospital, Bangalore, and further validated by radiologists from the same hospital. Comparing the simulated results, the proposed adaptive model MAMIF produced superior visually fused images compared to other approaches such as MDMIF and MMDWT.

More »»

2021

R. R. Nair and Dr. Tripty Singh, “An Optimal Registration on Shearlet domain with Novel Weighted Energy fusion for Multi-Modal Medical Images”, Optik, vol. 225, p. 165742, 2021.[Abstract]


Medical images usually display various attributes of data on human viscera and abnormal tissue in different modalities. The fusion of images, ensures effective deployment of all relevant information from several modalities into a single image. Finally, the paper leads to a novel multi-modal medical image fusion method based on Non-Subsampled Shearlet Transform (NSST) called Denoised Optimum B-Spline Shearlet Image Fusion(DOBSIF) that is based on real-time and standard radiological datasets. The proposed, novel registration based fusion technique DOBSIF, is compared with existing state-of-art techniques like PCA, DWT, SWT etc., and in comparison the proposed DOBSIF works effectively for both the color and grayscale images. To improve the fusion function, a novel pre-fusion method is carried out with the help of the Whale Optimization Algorithm(WOA), using the ideal B-spline-based registration method and in addition a novel Weighted Energy fusion rule is applied to derive relevant information from the source images. The proposed work initially follows normal pre-processing measures such as Gaussian filtering, edge sharpening, and resizing followed by optimal registration, fusion with novel fusion rule and segmentation of tumor part from the fused image. The visual quality of the fused image was evaluated by expert radiologists and the fused resultant image is robust, subject to the modified Active Contour(ACM) model for lesion identification.

More »»

2020

J. Varghese, Dr. Tripty Singh, Bhat, V., and Kuriakose, M., “Segmentation and Three Dimensional Visualization of Mandible Using Active Contour and Visualization Toolkit in Craniofacial Computed Tomography Images”, Journal of Computational and Theoretical Nanoscience, vol. 17, no. 1, pp. 61–67, 2020.[Abstract]


Three-dimensional representation of facial bone surface is needed in the virtual surgical planning for orthognathic surgery. Segmentation of facial bone surface from computed tomography images is first step in developing the 3D model. This paper focuses on segmentation of mandible bone using active contour segmentation of Insight Segmentation and Registration Toolkit library. The results are given as 3D stereo lithographic image. The result is compared with the ground truth image segmented by an expert radiologist. Various evaluation metrics are used for finding the segmentation accuracy and the result has given segmentation accuracy of 97.50%. Therefore, this method can be used as an initial step in automatic cephalometric land marking, an important task in virtual surgical planning for orthognathic surgery.

More »»

2020

R. R. Nair and Dr. Tripty Singh, “Multi-Modal based MSMIF using Hybrid fusion with 1-D Wavelet Transform”, IJAST, vol. 29, no. 05, pp. 5353–5368, 2020.[Abstract]


Multimodal fusion images minimize redundancy and increase the required data from the input imagery of various medical imagery sensors. The first and foremost goal is to establish a single fused image that could be more useful for successful clinical research. This work introduces a combination of two phases of hybrid processes, such as the SWTPCA and the One Dimensional-Discrete Wavelet Transform (1D-DWT) fusion of DWTPCA. The Laplacian based 1D-DWT is hybridized with combinations of WT (Wavelet Transform) and PCA (Principal Component Analysis). In this work, proposed two different hybrid algorithms, that are discussed in various sections of this paper. PCA fuses the approximation components to reduce the redundancy of both source images and to improve SWT's limit on non-directionality. To enhance the visual clarity of the image, the information components are fused with the Sum Modified Laplacian (SML). The suggested approach has been demonstrated by many sets of medical images in real-time. The paper demonstrates comparative assessments based on subjective and objective evaluation.

More »»

2019

T. Babu, Dr. Tripty Singh, Gupta, D., and Hameed, S., “Prediction of Normal & Grades of Cancer on Colon Biopsy Images at Different Magnifications using Minimal Robust Texture & Morphological Features”, International Journal of Bioinformatics Research and Applications, (Communicated), 2019.

2019

R. R. Nair and Dr. Tripty Singh, “Multi-sensor medical image fusion using pyramid-based DWT: a multi-resolution approach”, IET Image processing journal (Scopus Indexed), vol. 13, no. 9, pp. 1447 – 1459, 2019.[Abstract]


Generally, image fusions are carried out on two-dimensional (2D) images, but the operations with the 2D images increase the computational complexity than vector data. This study presents an algorithm with Laplacian pyramid built on 1D discrete wavelet transform (DWT) called modified multi-resolution DWT (MMDWT) for multi-sensor medical image fusion which was found to be efficient for n-level decomposition and can work with all mother wavelets with less computational complexity. The MMDWT methodology is compared with the discrete cosine transform, DWT, stationary WT, curvelet transform, principal component analysis, fuzzy and neurofuzzy technique and the performance measure is analysed. The performance evaluation of the MMDWT technique is illustrated using several sets of medical images provided by Health Care Global Enterprises Ltd. (HCG) Hospital Bangalore, based on the subjective and objective analyses. The result is validated by radiologists from HCG for subjective evaluation. The outcome of the MMDWT methodology is analysed with existing fusion algorithms and reveals the supremacy of the final fusion results.

More »»

2018

J. V. and Dr. Tripty Singh, “Segmentation and 3D Visualization of mandible using Active Contour and Visualization Toolkit in Craniofacial CT Images”, International Journal of Computational and Theoretical Nanoscience , 2018.

2015

G. Joseph, Dr. Tripty Singh, Andan, H. M., and Aravind, G., “Registration Plate Recognition from Still Images and Videos in Real Time Conditions”, International Journal of Computer Science and Information Technologies, vol. 6, no. 3, pp. 2729-2734, 2015.[Abstract]


Registration plate recognition plays a vital role in numerous numbers of applications in today’s world. Researches done so far could not completely meet the real time requirements of the system like different color, shape and size of plates, varied illumination conditions at image capture time, different positions and alignment of the plate. In the proposed system we introduce dynamic image processing techniques to meet the above mentioned short comings. We also introduce a new approach using genetic algorithm to find the location of the plate. Fluctuating illumination conditions are taken care-off by adaptive threshold method. Connected component labelling is used to identify the objects in blind folded regions. A matrix of invariant scale geometry is used for better system adaptability when applied to different plates. The convergence of the genetic algorithm is greatly improved by the introduction of a newly created mutation and crossover operators. We also modify genetic algorithm to overcome the drawbacks of connected component method by importing partial matching of the characters.

More »»

2014

Dr. Tripty Singh and Kumar, B., “Implementation and Study of Performance Analysis of Various Classifiers on Mammograms”, International Journal of Advanced Information Science and Technology (IJAIST), vol. 28, 2014.

Publication Type: Conference Proceedings

Year of Publication Title

2020

N. Oruganti and Dr. Tripty Singh, “Best Fit Polygonal Approximation for Multiple ROI Estimation”, 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT). 2020.[Abstract]


Best Fit Ploygonal Approximation for Multiple ROI Estimation is a difficult activity and most computerized imaging applications require it as a preprocessing step. Among different calculations, albeit part and consolidation (SM) calculation is profoundly utilized on account of its straightforwardness and adequacy in fragmenting homogeneous districts, be that as it may, it can't portion a wide range of items in all pictures. The motivation of the research work is to find multiple region of interest in single image. It is useful for radiologists to identify an ROI position relative to another ROI. It is beneficial if multiple measurements of various tissue structures are to be made in single slice. This paper addresses multiple ROI of different shapes and structures. To detect homogeneous parts it is important to extract only those affected regions which are possible with the help of ROI (region of interest). ROI is a part of an image which you want to separate from the original image. It is generally used to mask voxels. In this research paper we mainly focus on multiple ROI where the original image will be split into different regions with the help of split algorithm and apply any of the ROI extraction technique to extract the effected piece and merge them using merge algorithm and finally image reconstruction is done to get the required image.

More »»

2020

N. Oruganti and Dr. Tripty Singh, “Modified Hough Transformation for ROI”, 2020 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT). 2020.[Abstract]


Region of interest (ROI) plays major role in the field of Radiology. It's a field of medicine that characterized for clinical health care and transmission of medical images and videos. The aim of ROI extraction is to decide which part of the brain image is affected. For transference of high resolution images, good compression techniques are needed. This is an important aspect in compressing resolution of images by avoiding process of unwanted image points. It provides better extraction techniques for better image extraction. In this paper, the modified Hough transformation technique which is the combination of both manual and automatic techniques is used. This technique was compared with different other techniques and provided good results. Some of the ROI classifications are discussed in literature review and implemented free-hand technique and automatic technique for extraction of important region in images.

More »»

2020

R. R. Nair, Karumanchi, S. H., and Dr. Tripty Singh, “Neuro-Fuzzy based Multimodal Medical Image Fusion”, 2020 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT). IEEE, 2020.[Abstract]


The role of fusion of images in determining the quality of medical images for diagnosis and treatment planning is important. Present work deals with fusion in wavelet domain with approximation components applied with Principal Component Analysis(PCA) fusion rule and detailed components with Neuro-Fuzzy rule. The pca helps to keep structural information in each position. Neuro-Fuzzy computing allows better intelligent decision-making in the selection of detailed components. The proposed algorithm provides better visualization and tissue structure of the organ. The proposed algorithm can work for both color as well as grayscale images. The proposed fusion algorithm tested with four pairs of data sets which are collected from defense journal. Well-known quantitative measures and subjective assessment by a team of expert radiologists validates the study of the proposed algorithm.

More »»

2019

Dr. Tripty Singh and Karanchery, S., “Universal Image Segmentation Technique for Cancer Detection in Medical Images”, 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT). 2019.

2019

Dr. Tripty Singh and Babu, T., “Fractal Image Processing and Analysis for Compression of Hyperspectral Images”, 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT). IEEE, 2019.[Abstract]


Hyperspectral imaging is a technique in which the information is collecting and processing across an electromagnetic spectrum. Fractal Image Processing deals with various dimensions of an image. Hyperspectral analysis are applied on multiple frequency bands of images, and produces spatial and spectral information. HSI can elongate 390 to 700 nm i.e UV to infrared and near-infrared wavelength regions. This technique based system engenders narrow band(<; 390 to 700 nm>) images of different wavelengths. By utilizing HIS, visualization can be elongated to invisible wavelengths. Hyperspectral based techniques have applications in various fields such as medical diagnosis, agriculture, food processing, remote sensing etc. In this project, the compression of hyperspectral images is considered. Present work involves Modified DCT-Discrete Cosine Transformation based image compression. Compared with the convention lossless compression techniques of the benchmark multi-component and hyperspectral (JPEG2000), the MOD-DCT lossless algorithm produces considerable reduce in compressed file size for beyond visible range. After implementation of Modified DCT for hyperspectral images high compression ratio was achieved.

More »»

2019

Jithy Varghese, Dr. Tripty Singh, Bhat, V., and Kuriakose, M., “Analysis of Three –Dimensional Volume Rendering of Craniofacial CT Images using Marching Cube and Ray Casting Algorithm”, International Conference on Recent Trends in Electronics, Information & Communication Technology . Sri Venkateshwara College of Engineering, Bengaluru, India, 2019.

2019

S. Pramod G. and Dr. Tripty Singh, “Tetrahedral 3D Mesh Generation for Medical Images”, International Conference on Recent Trends in Electronics, Information & Communication Technology. Sri Venkateshwara College of Engineering, Bengaluru, India, 2019.

2019

R. M.S.P, Mahakalkar, N. A., and Dr. Tripty Singh, “Novel Approach for Detection of Early Diabetic Retinopathy”, 3rd International Conference on Inventive Systems and Control (ICISC 2019). JCT College of Engineering and Technology, Coimbatore , 2019.

2019

M. P, Dr. Tripty Singh, Nayar, D. Ravi, and Kumar, D. Shiv, “Multi Modal Medical Image Fusion Using CNN”, 3rd International Conference on Inventive Systems and Control (ICISC 2019) . JCT College of Engineering and Technology, Coimbatore, 2019.

2018

R. Mukkamala Neeraja, Pamidi, S., Babu, T., and Dr. Tripty Singh, “Developing Deep PCANet for Breast Cancer staging on Histopathological Data”, International Conference on Advances in Computing, Communications and Informatics (ICACCI). PES, Bengaluru, 2018.

2018

D. N. Vinod and Dr. Tripty Singh, “Autonomous Agricultural Farming Robot in Closed Field”, 2018 3rd IEEE International Conference on Recent Trends in Electronics, Information Communication Technology (RTEICT). IEEE, Bangalore, India, 2018.[Abstract]


Present research strives to implement the agricultural farming robot which can move instinctively, instinctively, involuntarily for ploughing, seeding and irrigation in closed field. This research also contributes to enhance functionality of Agri-Bot in the field for spying. The agri robot is equipped with a camera and sends the data to pc through Wi-Fi network. The robot has ploughing blades and servo motor for distributing the seeds and irrigation into the field. It works with ultrasonic sensor and IR sensor. Ultrasonic sensor is for avoiding obstacles in the field, IR sensor is for sensing felid boundary. Arduino controller acts as heart and brain of the system, it makes fast, accurate, autonomous movement. Video acquisition and transmitting camera mounted on it is 360° rotatable. This Research features a Agri-Bot that uses Wi-Fi 802.11G along with TCP/IP protocol. IP address and Video is received in laptop for further processing. This research intends to reduce human efforts and provide an intelligent aid to the farmers.

More »»

2017

D. David and Dr. Tripty Singh, “Estimation of Field of View on Human Fundus Image”, International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS 2017). Chennai, 2017.[Abstract]


Quality analysis of fundus image is the main idea of this work. In case of diabetic patients, the surface of a glaucomatous retinal disc can slope steeply into the cup, this may affect the inner anatomy of retinal disc and thus the reduction in the optical disc size. In this project fundus image of any quality is taken and has been acquired into our system, finally deduce if it is a good or a bad quality image. The two parameters used for assessing the quality of the images are non-uniform intensity and stray light. In non-uniform intensity method if the shape match indexing (SMI) value is lesser than 97.5 then the image falls under bad quality. And in the Stray light method, based on the size of the area, if it is greater than 4000 it is concluded that our image has Stray light and it is a bad quality image. In the end comparison and contrast is made based on the parameters. Also, the noises that are present in the image is also brought into focus and eliminated. The results to calculate the accuracy, specificity and sensitivity based on the field of view and resolution is also considered.

More »»

2017

A. Sahay, Dr. Tripty Singh, Karthik, G., and Angadi, S., “Optimal election winning search algorithm for distributed systems”, 2017 2nd International Conference on Telecommunication and Networks (TEL-NET). IEEE, 2017.[Abstract]


This paper presents the utilization of an Optimal Election Winning Search Algorithm (OEWSA) to optimally design the search algorithm for distributed systems. The effectiveness of the proposed Optimal Election Wining Search Algorithm (OEWSA) is compared to the Breadth First Search (BFS) and Depth First Search (DFS) search algorithms. The validity of the proposed algorithm is verified by the simulation results which are performed using Eclipse. Simulation results reveal that the OEWSA approach performs better in terms of delivery accuracy as applied to minimize power loss along with degree centrality, bandwidth and buffer length of the nodes of a distributed system with increased number of nodes and improves distribution system reliability.

More »»

2017

Dr. Tripty Singh and Das, S., “Energy Aware Routing Protocol for Ad-Hoc Networks”, International Conference on Innovations in Control, Communication and Information Systems (ICICCI-2017). Delhi-NCR, Greater Noida, India, 2017.

2017

Dr. Tripty Singh and , “Multinomial Logistic Regression and Hybrid GLCM for Cervical Cancer Diagnosis and Prognosis”, International Conference on Innovations in Control, Communication and Information Systems (ICICCI-2017). Noida, India, 2017.

2017

Dr. Tripty Singh, “Foggy Image Enhancement and Object Identification by Extended Maxima Algorithms”, International Conference on Innovations in Control, Communication and Information Systems (ICICCI-2017) . Noida, India, 2017.

2017

H. Singh and Dr. Tripty Singh, “Reinforcement Learning based Search algorithm in Social Network”, International Conference On Smart Technologies For Smart Nation (SmartTechCon2017). Reva University,Bengaluru, 2017.

2017

R. R. Nair, Dr. Tripty Singh, Nayar, R., and Kumar, S., “Modified Level Cut Liver Segmentation from CT”, 9th International Conference on Advanced Computing (ICoAC 2017). MIT, Chennai, 2017.[Abstract]


For liver surgical planning accurate segmentation of liver vasculature from abdominal CTis very significant[39]. Study on the liver vessel structure helps to locate the tumor. But segmentation of CT Liver vasculature is not easy task because of artifacts, complex structure[11] of liver anatomy. The main two vasculature structures among the four different tubular systems are the portal(main) and hepatic veins inside liver[37]. It is not so easy to segment and differentiate among them because of the twist, curved, obstruct each other nature and sometimes distorted by liver lesions. Also poor contrast and imperfect volume effect adds difficulties on automatic vessel segmentation of liver. In this we present a novel work on automatic vasculature segmentation of Liver derived from modified level set method. Secondly Liver region is extracted from CT abdominal image using cropping. Finally, modified level cut method is used to segment vessels of liver from background voxels. Experimental outcome shows that the proposed technique can efficiently segment liver vessels from CT abdominal images. The proposed technique has been evaluated on 300 clinical CT images collected from HCG Cancer Research Hospital.

More »»

2017

T. Babu, Dr. Tripty Singh, Dr. Deepa Gupta, and Hameed, S., “Colon Cancer Detection in Biopsy Images for Indian Population at Different Magnification Factors Using Texture Features”, 9th International Conference on Advanced Computing (ICoAC 2017). MIT, Chennai , 2017.

2017

R. R. Nair and Dr. Tripty Singh, “Logistic Regression for Mouth (orotracheal) or nose (nasotracheal) Endotracheal Intubation”, International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI-2017), . IEEE, Saveetha Engineering College Chennai , 2017.[Abstract]


This research is fueled by the growing increase in the cases of mallampatti left undiagnosed. Mallampatti is the most common and lethal disease these days. In order to help radiologist examine different stages of Mallampatti, Polinomial Logistic Regression Classifier helps them to interpret images. The dataset of 400 images have been collected from HCG Hospital Bangalore that contains both 2D and 3D mallampatti images. First images are de noised using median filters. Removal of noise will help in increasing the accuracy of classifier, hence detecting cancer at the early stage. Secondly, Region of interest (ROI) are extracted for several slides. Thirdly, Texture Analysis Using the hybrid Gray-Level Co-Occurrence Matrix is done where GLCM features like entropy, energy, auto correlation etc are extracted. At last these Texture Features serve as inputs to proposed classifier Polinomial Logistic Regression to detect the normal, early and late stages of mallampatti. The proposed Classifier is also compared with mallampatti score for accuracy, precision, reliability and Compression ratio.

More »»

2017

A. R. Doke and Dr. Tripty Singh, “Comparative Analysis of Wavelet Transform Methods for Fusion of CT and PET Images”, International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI-2017), . Saveetha Engineering College, Chennai, 2017.[Abstract]


Medical 2-D Data fusion is process of combining two or more different types of 2-D Data which in this case is CT and PET Scan images having different morphological structure as a one image so that the fused image will reflects more feature as compare to original image fusion process of two images aims to get a more in depth analysis of the picture. Fusion of 2-D Medical Data produces the anatomical details which single image fails to deliver. This useful information obtained from fused medical images are used by the surgeons and radiologist for treatment planning and computer aided surgeries. There is need to combine more information so that fused image will be more accurate for human perception as well as computer processing. This research is intended to analyze fusion of CT and PET images by using various basis function by using seven mother wavelets. This research further explores the analysis of the performance of each mother wavelet on anatomical features in termsof accuracy and precision.

More »»

2016

Dr. Tripty Singh, “Modeling architecture for telecomm services and computing the improvement attained on key performance indicators”, Proceeding - IEEE International Conference on Computing, Communication and Automation, ICCCA 2016. Institute of Electrical and Electronics Engineers Inc., pp. 1325-1331, 2016.[Abstract]


In today's era of communication, a company's brand is driven by more than the combination of promises made and promises kept for customer satisfaction to gain popularity of brand name. A telecommunications service provider's survival depends on its ability to prepare for changes in customer needs, as well as changes in regulation and technology. But the increasing expectations of customers and the introduction of many new services and technologies is making it difficult to comprehend and meet customer requirements. Therefore, in this paper the background of transformation in the telecommunication companies is analyzed. As in the rest of the competitors, a performance indicator or key performance indicator (KPI) is a measure of performance. Such measures are commonly used to help an organization define and evaluate how successful it is, typically in terms of making progress towards its long-term organizational goals. From the characteristics of telecommunication services, this paper makes the evaluation method of the quality of telecommunication services based on customer experience. Evaluation method designs for ASR and CCR are considered to determine the quality of telecommunication services and the factors contained in various genes. The implementation of the newly proposed architecture was carried out at TELECOM-SOUTH Telecom sector 1 and Telecom sector 2 solution. TELECOM-SOUTH Region KPI's were analyzed on MetaSol software. Hence, this paper makes an analysis on real cases in telecommunication. © 2016 IEEE.

More »»

2015

Dr. Tripty Singh, K, J. Varghese, Joseph, G., H.M., A., and G., A., “Parametric Free Kernel Based Fuzzy C Means Algorithm in Color Image Segmentation”, International Conference on Emerging Trends in Engineering, Business and Disaster Management(ICBDM 2015). Noorul Islam University, Kumaracoil, Tamilnadu,India, 2015.

2015

A. H.M., Dr. Tripty Singh, G., A., and Joseph, G., “Web Security: A prototype Tool for Detecting Web Application Vulnerability”, International Conference on Emerging Trends in Engineering, Business and Disaster Management(ICBDM 2015). Noorul Islam University, Kumaracoil, Tamilnad, 2015.

2014

Dr. Tripty Singh, “Novel Restoration Process for degraded Image (Development of GUI for Restoration of Degraded Image by different filters)”, Fifth International Conference on ‘Signal and Image Processing. 2014.[Abstract]


Restoration techniques of degraded image is still a challenging task, in spite of the sophistication of the recently proposed methods. All show an outstanding performance when the image model corresponds to the algorithm assumptions but fail to retain the edges and fine structure. In this paper, a novel approach for image restoration has been developed. To show the analysis of performance of this noel restoration procedure GUI has been developed. It shows the Restoration of Degraded image on various noises by different Filters. In implementation of the approach first, image is degraded by adding different types of noises in sample images and then convolving images with different kinds of filters (Mean Filters, Min and Max Filters). Proposed image restoration method’s analysis on performances of denoising techniques Graphical User Interface has been developed as a part of this research. In this paper true colour sample images are degraded with different noise and then is restored back. The performance analyis of the present approach with state of art techniques are in terms of mean square error, peak signal-to-noise ratio, and normalized absolute error is also provided. In comparisons with other state of art methods, present approach yields better to optimization, and shows to be applicable to a much wider range of noises

More »»

2014

Dr. Tripty Singh and S, A., “Obstacle Detection for Navigation of Robot Using Computer Vision and Laser Rangefinder”, International Conference on ‘Recent Trends in Electrical and Electronics Engineering (ICRTEEE)’. 2014.

2014

S. S. and Dr. Tripty Singh, “New Technique for Image Enhancement In Biomedical Applications (For MRI, CT, MAMMOGRAM AND ULTRASOUND)”, International Conference on ‘Recent Trends in Electrical and Electronics Engineering (ICRTEEE). 2014.

2014

Dr. Tripty Singh and K., J. Varghese, “Development of an Intelligent Recognition System using Iris and Sclera Features”, ICCTAC International Conference on ‘Current Trends in Advanced Computing’. Kristu Jayanti College, Bengaluru, 2014.

2014

Dr. Tripty Singh, K., N., and R., M., “A Novel Method of Head Tracking Cursor Control System Using Open CV”, International Conference on ‘Computer Science, Electronics and Communication Engineering (ICCECE). Institute for Research & Development India (IRD), Pune, Maharashtra, 2014.

2014

Dr. Tripty Singh, Mohan, S., and K, J. Varghese, “PCB Thermal Image Analysis using MATLAB”, International Conference on Information and Communication Technologies (ICICT, 2014). Tirupati , 2014.[Abstract]


This paper explains a method for Printed Circuit Board (PCB) thermal image analysis using MATLAB. In this method, a train of thermal images of the PCB in chronological order are used as input. Each image corresponds to a maneuver or a particular loading condition of the PCB. The two parameters used for analysis are peak temperature and maximum area of the peak temperature which co-relate with the heat dissipation regions. This program provides a MATLAB based Graphical User Interface (GUI) for the design engineer to select the most critical image from the lot, see the temperature jump (in the form of difference image) and view the series of images in the form of a video for quick analysis

More »»

2014

Dr. Tripty Singh, V.V.V.S.N., B. K., and R., M., “BER and LLR Analysis with MC-CDMA using BPSK/ QAM Techniques for Wireless Communication”, International Conference on Information and Communication Technologies (ICICT, 2014). Tirupati, 2014.

2014

Dr. Tripty Singh and Mishra, S., “Image Vector Classification Algorithm for Hand-Writing Verification”, International Conference on Advances in Computing, Communications and Informatics (ICACCI). Greater Noida, India., 2014.[Abstract]


In this paper, we propose and implement the data mining techniques for verification of hand-writing recorded in an image. The captured images are considered independent of writing material in this system. This system consists of six submodules. Namely, i) Sample image data acquisition and preprocessing; ii) Vectors generation; iii) Computation of clusters; iv) Cluster Head Computation v) Pattern Parameter Extraction; vi) Result. The first sub-module captures and categorizes the image for preprocessing. These preprocessed images are vectored and a cluster is computed based on thea) degree of entropy in the vectors. Therefore, these bunch of clusters represent themselves with the degree of entropy, type of cluster by choosing a cluster head. Finally, the parameters such as the distance, entropy, confidence, are extracted from the clustering; and a result is generated for the given set of samples.

More »»

2014

Dr. Tripty Singh, “Novel Restoration Process for degraded Image”, Proceedings - 2014 5th International Conference on Signal and Image Processing, ICSIP 2014. IEEE Computer Society, Bangalore, Karnataka, 2014.[Abstract]


Restoration techniques of degraded image is still a challenging task, in spite of the sophistication of the recently proposed methods. All show an outstanding performance when the image model corresponds to the algorithm assumptions but fail to retain the edges and fine structure. In this paper, a novel approach for image restoration has been developed. To show the analysis of performance of this noel restoration procedure GUI has been developed. It shows the Restoration of Degraded image on various noises by different Filters. In implementation of the approach first, image is degraded by adding different types of noises in sample images and then convolving images with different kinds of filters (Mean Filters, Min and Max Filters). Proposed image restoration method's analysis on performances of denoising techniques Graphical User Interface has been developed as a part of this research. In this paper true colour sample images are degraded with different noise and then is restored back. The performance analyis of the present approach with state of art techniques are in terms of mean square error, peak signal-to-noise ratio, and normalized absolute error is also provided. In comparisons with other state of art methods, present approach yields better to optimization, and shows to be applicable to a much wider range of noises. © 2014 IEEE.

More »»

2013

Dr. Tripty Singh, “Design of New Pattern Classifier based on Morphological Parameter”, International Conference on Electronics and Electrical Engineering. Graduate Research in Engineering and Technology (GRET), IRNet INDIA at Hyderabad , pp. 40 – 46, 2013.

2013

Dr. Tripty Singh, “Designing of new Template Matching Algorithm for Object Tracking”, International Conference on ‘Current Trends in Advanced Computing (ICCTAC)’. KJCMT,  IJCA and ISRO at Bengaluru, 2013.

2013

Dr. Tripty Singh, “A Curvelet Averaging and Filtering based Algorithm Development of GUI for Denoising Mammograms Using Conventional and Proposed Algorithm”, Seventh International Conference on Image and Signal Processing (ICISP-2014) . Elsevier Publications 2013 ICSIP, University Visvesvaraya College of Engineering Bengaluru , pp. 247–256, 2013.

Publication Type: Conference Paper

Year of Publication Title

2020

R. R. Nair, Dr. Tripty Singh, Sankar, R., and Gunndu, K., “Multi-Modal Medical Image Fusion Using LMF-GAN - A Maximum Parameter Infusion Technique”, in Sixth International Symposium on Intelligent Systems Technologies and Applications (ISTA'20) , 2020.

2019

R. M Sampreeth, Sravani, N., and Dr. Tripty Singh, “Real Estate Price Prediction”, in International Conference on Recent Trends in Electronics, Information & Communication Technology, Sri Venkateshwara College of Engineering, Bengaluru, India, 2019.

2019

Dr. Tripty Singh, “New Canny-CLAHE Method for Micro Aneurysms Detection”, in (ICCCNT 2019) 10th International Conference on Computing, Communication and Networking Technologies, IIT, Kanpur, India, 2019.

2019

S. Pramod and Dr. Tripty Singh, “3D Mesh Generation for Craniofacial CT Images”, in 3rd International Conference on Inventive Systems and Control (ICISC 2019), JCT College of Engineering and Technology, 2019.

2019

Dr. Tripty Singh, “Constrained Markov Decision Processes for Intelligent Traffic”, in 2019 10th International Conference on Computing, Communication and Networking Technologies (ICCCNT), 2019.[Abstract]


Traffic congestion has become a serious problem as most of the roads are busy and has to suffer vehicular traffic at an increasing rate. Proficient Signaling Systems are indispensable for reducing traffic congestion at intersections. This work tries to design a model according to constraint markov decision process for a given reinforcement learning problem statement which prediction of traffic congestion at the intersection and lanes in a busy roads. A Green Light Simulator is used to simulate real time data set of the Bangalore Roads and Traffic. After that several TLC algorithms are run and efficiency is computed manually. In the third step policy is build using parameters that contain features like acceleration, velocity, no of vehicles plying on the road. Based on these parameters, the policy generated helps to predict congestion at the busy roads. The dataset includes traffic data from Bangalore Roads.

More »»

2018

Dr. Tripty Singh and Dasari, V. Naga, “Autonomous Agricultural Farming Robot in Closed Field Autonomous Farming and Surveillance Bot”, in 3rd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT), Organised by Department of Electronics & Communication Engineering (Accredited by NBA) , Sri Venkateshwara College of Engineering, Bengaluru, 2018.

2018

R. R. Nair and Dr. Tripty Singh, “Multi-sensor, Multi-modal Medical Image Fusion for Color Images: A Multi-resolution Approach”, in 2018 Tenth International Conference on Advanced Computing (ICoAC), 2018.[Abstract]


Multi-modal medical image fusion techniques and equipment plays remarkable attainments in increasing the medical accurateness of judgments related to images in medical. The important goal of the paper is to produce a unique image(fused), aimed at an effective medical examination with enhanced vital information. This paper presented an algorithm using Multi-Resolution Discrete Wavelet Transform(MDWT) to fuse RGB medical images like Computed Tomography(CT), Magnetic Resonance T1 (MRT1), Magnetic Resonance Angiogram(MRA), Positron Emission Tomography(PET) and Single Photon Emission Computed Tomography(SPECT) and was found to be efficient for color and grayscale images. MDWT is compared with existing Principal Component Analysis(PCA) and Discrete Sine Transform(DST) using four sets of medical images collected from Defence journal. The MDWT methodology fused images give better performance than other two algorithms. The performance evaluation of the final fused image is based on the subjective and objective analysis. The result is validated by research scholars from Amrita School of Engineering for subjective evaluation.

More »»

2018

P. Tyagi, Dr. Tripty Singh, Nayar, R., and Kumar, S., “Performance Comparison and Analysis of Medical Image Segmentation Techniques”, in IEEE International Conference on Current Trends in Advanced Computing (ICCTAC-18), , Bangalore, India, 2018.[Abstract]


This research aims at performance analysis and comparison of medical image segmentation techniques for surgical application. Existing algorithm when applied on digital images it can avoid problems such as noise and signal distortion during processing. In this Researchers, authors have studied 500 CT images for performance analysis of the algorithms. Images were provided by HCG Oncology Hospital, Bengaluru for pilot study. This paper shows implementation and analysis of conventional Segmentation Protocol for CT Head and Neck Images. Later part of the research deals with designing of an efficient protocol which does segmentation with pseudo coloring of segmented area which makes images visually efficient to extract the structure. This designing requires three steps the pre-segmentation followed by indexing of gray level with pseudo-color map and comprehensive edge detection. Due to effective use of pseudo coloring the inside anatomical structure of craniofacial portion the noise has no effect on the segmentation results. ITK-SNAP Medical Image Segmentation Tool is used for Simulation. MATLAB is used for implementation of proposed segmentation model. The resultant images are more clear, closed, continuous, more accurate for abnormality detection.

More »»

2017

Dr. Tripty Singh, Jha, R., and Nayar, R., “Mammogram Classification using Multinominal Logistic Regression”, in International Conference on Communication and Signal Processing-ICCSP’17 , Adhiparasakthi Engineering College Melmaruvathur, 2017.

2017

Dr. Tripty Singh, “Foggy Image Enhancement and Object Identification by Extended Maxima Algorithm”, in 2017 International Conference on Innovations in Control, Communication and Information Systems (ICICCI), Greater Noida, India, 2017.[Abstract]


Clear vision is very important while driving regardless of any environmental conditions or mechanical challenges. To overcome the difficult conditions and external challenges of human vision while driving a vehicle, image processing techniques can be used. This paper mainly deals with the difficult conditions like poor lighting in the roads, difficult lighting scenarios, and atmospheric conditions like fog/dust/haze and smoke. This paper also finds an approach to find the moving objects using the extended maxima algorithm and extraneous feature removal algorithm. This also directs a research towards object detection in foggy driving. In foggy weather contrast image enhancement and identifying the nearby objects is possible with image enhancement techniques. This helps the driver to avoid any accidents due to poor vision and thus to save human lives.

More »»

2017

Anandapadmanabhan and Dr. Tripty Singh, “Monitoring Driver’s Behavior Using Acceleration Sensor”, in ICPCSI International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI-2017) , 2017.

2017

A. Arjun and Dr. Tripty Singh, “Analysis of image segmentation methods on Amrita's Indian side face profile database”, in Proceedings of the 2017 IEEE International Conference on Communication and Signal Processing, ICCSP 2017, 2017, vol. 2018-January, pp. 952-958.[Abstract]


Amongst an array of research topics, image segmentation is the most challenging one. This along with image thresholding are the fundamental problems that arise in image processing. There are 2 main methods in image segmentation. They are automatic and manual. In the automatic method, we do not require any person to operate on the segmentation, whereas in the manual very minimal user interaction is required. It is proven that the interactive or the manual approach gives a better result than the automatic approach. This paper focuses on the comparisons and the implementations of the segmentation methods and their analysis. It also gives insights whether automatic or manual methods are better. The algorithms that we used here are modified Level Set algorithm, Gaussian Mixture model, Support Vector Machine. Finally, all the results are obtained and are compared and contrasted. © 2017 IEEE.

More »»

2016

Dr. Tripty Singh, “Design of a dual biometric authentication system”, in 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), Chennai, India, 2016.[Abstract]


Present research is on the combination of two biometric identification and recognition, i.e., iris pattern based and contours of fingerprint based, for identification and hence authentication. From the pre processed iris images of any person and fingerprint, the contours and countourlets are obtained. Localization followed by a normalization of an iris image is given for feature extraction using Gabor convolution, while minutia extraction of an enhanced finger print image is done using Crossing Number method. These features of contours and countourlets obtained from a sampled stream and in order to get the matching scores, they are estimated with samples in database. Comparison techniques used are hamming distance and Euclidean distance respectively for iris and fingerprint. Pattern of similarity and difference of scores are obtained after the passing of matching to the combination module. The score obtained finally is used to inform whether the person is authenticated or a bluffer. For a critical situation both the scores need to be matched i.e., for high security related applications both the scores need to be matched individually so that the combination will give better results. For some non critical application any one of the traits need to be matched so that the genuine persons would not miss a chance.

More »»

2016

S. Das and Dr. Tripty Singh, “Lifetime Optimization Secure Routing (LOSER) Protocol Design for Wireless Sensor Networks”, in IEEE International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT) – 2016, DMI College of Engineering- Chennai, India, 2016.

2016

J. Mary C. and Dr. Tripty Singh, “Cost Optimization Using Intelligent Resource Provisioning in Cloud”, in 3rd IEEE international Conference on Electronics and Communication systems (IECS-2016), Coimbatore,India, 2016.

2016

Dr. Tripty Singh and C. Mary, J., “Development of Accurate Face Recognition Process Flow for Authentication”, in Emerging Research in Computing, Information, Communication and Applications ERCICA-2016, NMIT, Bangalore, 2016.[Abstract]


Rapid and tough trackingTrackingof multiple faces have many crucial applications in various fields like video surveillance and video conferencing. Hence, it gained lot of momentum from computer vision researchers. Initialization, tracking and display are the three important steps in real-time tracking of multiple faces in high-resolution videos. Out of which, tracking is quite intensive in computation. Object detection and tracking are important in many computer vision applications including activity recognition, automotive safety, and surveillance. In this paper, a computational model of real-time face tracking has been presented. The tracking problem into three parts: the region extractor is based on the integration of skin-color, motion, and silhouette features, while the face detectorFace detectionuses a simple, rule-based face detection algorithm, and SVMSupport Vector Machine (SVM). Real-time detection and tracking implementation has been carried out and results presented.

More »»

2015

A. G, M, A. H., Dr. Tripty Singh, and Joseph, G., “Development of biometric security system using CBIR and EER”, in 2015 International Conference on Communications and Signal Processing (ICCSP), Melmaruvathur, India, 2015.[Abstract]


The paper discusses about the content based image retrieval systems for biometric security. As image databases are growing at a rapid rate, demand for efficient and effective tools for retrieval of images increased significantly. Among them, content-based image retrieval systems (CBIR) have become very popular for browsing, searching and retrieving images from a large database of digital images. Biometric security methods have been gaining importance increasingly in the recent years due to advances in biometrics technology and its reliability and efficiency in real world applications. Biometric security methods take into account human's unique physical or behavioural characteristics that help to identify them. The proposed approach is based on three main features of an image: colour, texture and shape which can be incorporated into biometric security for effective security systems. The inclusion of fuzzy heuristics presents a increased accuracy on image retrieval than the existing approaches.

More »»

2015

G. Joseph and Dr. Tripty Singh, “Registration Plate Recognition Using Dynamic Image Processing and Genetic Algorithm”, in International Conference on Innovations in Computer Science & Engineering (ICICSE-2015), Singapore, 2015.[Abstract]


Registration plate recognition plays a vital role in numerous applications in today's world. We also introduce a new approach using genetic algorithm to figure out the registration plate location. Fluctuating illumination conditions are taken care-of by adaptive threshold method. Connected element tagging is used to identify the objects in blindfolded regions. A matrix of invariant scale geometry is used for better system adaptability when applied to different plates. The convergence of genetic algorithm is greatly improved by the introduction of a newly created mutation and crossover operators. We also modify genetic algorithm to overcome the drawbacks of connected element method by importing partial matching of the characters. Finally, we take a look at the real-time challenges and remedies to it.

More »»

2015

Dr. Tripty Singh and S, D. V., “A modern data architecture with apache Hadoop”, in 2015 International Conference on Green Computing and Internet of Things (ICGCIoT), Greater Noida on the beautiful campus of Galgotias Institutions , 2015.[Abstract]


This paper represents the analysis of the existing architecture framework used across domains. It also emphasizes on the modern architecture in integration with apache Hadoop. The existing data architecture is under pressure from new data and machine generated data for the upcoming years that is due to emergence of new data types there has been tremendous pressure on all the data systems within an enterprise over the years. An Exponential Growth has been estimated from 2.8 Zeta Byte of data in 2012 to grow to 40 Zeta Byte by 2020 and new data type growth is estimated to be eighty five percent with computer created information being expanded to 15 times all the more by 2020.

More »»

Publication Type: Book Chapter

Year of Publication Title

2019

Dr. Tripty Singh and Vinod, D. Naga, “Intelligent Farming With Surveillance Agribot”, in Applications of Image Processing and Soft Computing Systems in Agriculture, IGI Global, 2019.

2017

A. Kumar Wadhwani, Wadhwani, S., and Dr. Tripty Singh, “Computer Aided Diagnosis System for Breast Cancer Detection”, in Medical Imaging: Concepts, Methodologies, Tools, and Applications, 2017.

2015

A. Kumar Wadhwani, Wadhwani, S., and Dr. Tripty Singh, “Computer Aided Diagnosis System for Breast Cancer Detection”, in Optimizing Assistive Technologies for Aging Populations, IGI Global, 2015, pp. 378–395.[Abstract]


Management of breast cancer in elder patients is challenging due to a lack of good quality evidence regarding the role of adjuvant chemotherapy. Mammograms can depict most of the significant changes of breast disease. The primary radiographic signs of breast cancer are masses (its density, site, shape, borders), spicular lesions and calcification content. The basic idea is to convert the mammogram image and convert into 3-D matrix. Obtained matrix is used to convert the mammogram into binary image. Several techniques like detecting cell, filling gaps, dilating gaps, removing border, smoothing the objects, finding structures & extracting large objects have been used. Finally finding the granulometry of tissues in an Image without explicitly segmenting (detecting) each object. Compared to existing multiscale enhancement approaches, images processed with this method appear more familiar to radiologists and naturally close to the original mammogram.

More »»