Qualification: 
Ph.D, M.E
Email: 
s_padmavathi@cb.amrita.edu

S. Padmavathi, Associate Professor (Selection Grade) is associated with Amrita School of Engineering since 2001. She joined Amrita after securing ME in Computer Science Engineering from Government College of Technology, Coimbatore. She did her PhD in Hierarchical Digital Image Inpainting at Amrita Vishwa Vidyapeetham, Coimbatore. She has one year of teaching experience and one year of industry experience before her Master’s Degree. Her research interests are allied with Digital Image Processing, Video processing, Image Analysis and Pattern recognition. She is one of the faculty incharge for Smart Space Lab. She is a part of BoS and Doctoral committees of PhD candidates within and outside Amrita. She received Best Woman of the city award from Lions club in March, 2013 and Senior Woman Educator and Researcher Award from National Foundation for Entrepreneurship Development in March 2014.

She presented project proposals to funding agencies such as DST-TIDE and involved in various consultancy initiatives with industry such as Manatec, Sanofi etc. She has completed various academic Projects in Digital Image Inpainting, Vision based Fabric Defect Detection, fire detection, Number plate recognition, Vehicle detection and speed estimation, Traffic congestion analysis, face recognition, Face tracking, object tracking, Gait recognition, Gesture Recognition, Indian Sign Language recognition, Age Classification from facial Images , Conversion of Braille to text and speech in English, Tamil and Hindi , Night time video enhancement, Texture analysis and synthesis, Content based image retrieval using Texture, Wavelet based Image Compression, Image Mosaicking, Image Steganography ,Audio Steganography , Speech synthesis for native languages, Volume Visualization and Mesh Generation of Tomographic Images.

She was the Chair for a UG Session in “International Conference on Advanced Communication Systems” Organised by Govt. College of Technology, 2007. She severed as reviewer for various papers in International conference such as WICT 2011, CCSEIT-2012, SEAS-2012, WIMON2013, ITCSE 2013, ICCSEA-2013, ICAIT-2013, DPPR 2013, ACITY-2013, SIPP-2014, SCAI-2014, ITCSE-2014, ICONIAAC-2014, ICCSEA-2014, CSE-2014, AIAP-2014 etc. She has also reviewed paper for International Journals such as International Journal of Computer Science & Information Technology, International Journal of Software Engineering & Applications , Signal & Image Processing: An International Journal , International Journal of Information Sciences and Techniques, IET Image Processing, Applied Mathematics and Computation, Frontiers in Psychological and Behavioral Science(FPBS) , British Journal of Mathematics & Computer Science etc.

She has organized various workshops including “Introduction to Bioinformatic Algorithms and their Parallel Implementation”, Nov. 2001, GENESIS 06 – Online Project Contest- October 2006, Faculty Development Programme on Dr. Scheme with TCS, May 2009, “Recent Trends in Image Analysis” May 2009, “Cloud Computing” December 2009, ”Effective teaching learning of Computer programming” December 2009, IETE- National Technical Paper Contest, march 2012, National workshop on mobile applications and developer challenges in android powered devices , April 2014, National workshop on 3D Vision & multimedia streaming, May2014, Coding contest in Anokha2012 and 2015.

 She has delivered invited lectures on various topics of Image processing, Data Structures, Analysis of Algorithms across many colleges in Tamilnadu.

Honors and Awards 

  1. Best Woman of the city award by Lions club in March 2013
  2. Senior Woman Educator and Researcher Award by National Foundation for Entrepreneurship Development in March 2014
  3. Session Chair for a UG Session in “International Conference on Advanced Communication Systems” Organised by Govt. College of Technology on 10/01/2007

Publications

Publication Type: Conference Proceedings

Year of Publication Title

2021

S. Ajithkumar Panicker, Kumar, R. Vinod, Ramachandran, A., and Dr. Padmavathi S., “Analysis of Image Processing Techniques to Segment the Target Animal in Non-uniformly Illuminated and Occluded Images”, Inventive Communication and Computational Technologies. Springer Singapore, Singapore, 2021.[Abstract]


Non-uniformly illuminated images are a class of images that, from a subjective perspective, are difficult to analyze. The excess noise and the lack of properly defined boundaries all contribute to making these images a difficult dataset for any form of analysis or segmentation. This calls for proper feature extraction and specific enhancement to make these images ready for efficient information gathering. This paper aims to visualize the features that can be enhanced using image enhancement techniques to identify the target animal in a non-uniformly illuminated and occluded image, thereby enhancing the recognition power of the proposed system. This paper uses a method to approximately detect and locate the position of the animal in an image. Segmentation Using Region Adjacency Graphs, Interactive Foreground Extraction using GrabCut Algorithm and DeepLab model for semantic image segmentation have also been analyzed.

More »»

2020

U. Subbiah and Dr. Padmavathi S., “Analysis of Deep Learning Architecture for Non-Uniformly Illuminated Images”, 2020 International Conference on Inventive Computation Technologies (ICICT). 2020.[Abstract]


The use of deep learning to hone image processing techniques has become increasingly popular. Following the success of Convolutional Neural Networks (CNNs) for image classification, they have been tested for various applications. By training CNNs on a dataset with ground truth (light) images and the corresponding darkened version of the images, neural networks can be used for enhancement. This must account for the non-uniform illumination seen in night-time images. A novel method of training a neural network to enhance non-uniformly illuminated images is proposed. Further, the visualization of convolutional features extracted at each layer of the neural network is discussed, to understand which parts of an image helps the neural network identify the object, thereby enhancing its recognition power. The potential application of this system lies in detecting animals in the non-uniformly lit surveillance video, useful to settlements near forest regions, where wild animals pose a threat to the living areas.

More »»

2020

U. Subbiah, R. V. Kumar, Panicker, S. A., Bhalaje, R. A., and Dr. Padmavathi S., “An Enhanced Deep Learning Architecture for the Classification of Cancerous Lymph Node Images”, 2020 Second International Conference on Inventive Research in Computing Applications (ICIRCA). 2020.

2018

S. Krishnan, B.A. Sabarish, Gayathri V., and Dr. Padmavathi S., “Enhanced Defogging System on Foggy Digital Color Images”, Computational Vision and Bio Inspired Computing, Part of the Lecture Notes in Computational Vision and Biomechanics book series, vol. 28. Springer International Publishing, Cham, pp. 488-495, 2018.[Abstract]


Images which are captured using camera can cause degradation in images by the effect of climatic conditions such as haze and fog. Image restoration makes a notable change in performing different application of computer vision and pattern recognition. The main aim of this paper is to improve the effect of fog and hazy images compared to the existing methods. The enhanced defogging system [EDS] consists of different image improvement techniques with a Dark Channel Prior [DCP] Algorithm to estimate the amount of fog is there in the images and transmission as well. Fusion based fog removal will reduce the amount of haze remained in those images. Experiments were done more than 100 images and the results are discussed below.

More »»

2017

Sujee R. and Dr. Padmavathi S., “Image enhancement through pyramid histogram matching”, 2017 International Conference on Computer Communication and Informatics (ICCCI). IEEE, Coimbatore, India, 2017.[Abstract]


Pyramids being an emerging technology in the field of image processing, this paper uses the same for enhancing images using histogram matching. It gives a detailed analysis of enhancing the images by improving their contrasts using histogram matching in the pyramid layers thus extracting the information from the images to the maximum possible. It also shows the variation in the contrast of the images when matched with different sets of images of different contrasts.

More »»

2016

A. .A.V, .S, I., and Dr. Padmavathi S., “Geometric Correction For Braille Document Images”, Second International Conference on Signal and Image Processing, SIGPRO. pp. 35-46, 2016.

2015

Dr. Padmavathi S. and Abirami, G., “Differential Iilumination Enhancement Technique For A Night Time Video”, International Conference on Power, Circuit and Information Technology (ICPCIT-2015). p. 8, 2015.[Abstract]


Video surveillance has become a common security need in the present-world scenario. The nighttime video surveillance becomes more challenging due to the presence of extreme illumination conditions, which is not uniform in a frame. Pedestrian detection would be very difficult under such illumination condition. The system proposes a method to identify and segregate the differently illuminated regions with the help of day-time reference image. Various enhancement techniques are applied on these regions separately and the results are combined to obtain the enhanced frame. Results of these techniques are summarized and appropriate methods are suggested for specific cases.

More »»

2013

Dr. Padmavathi S., Dr. Soman K. P., and Aarthi, R., “Image restoration using knowledge from the image”, Advances in Intelligent Systems and Computing, vol. 177 AISC. Chennai, pp. 19-25, 2013.[Abstract]


There are various real world situations where, a portion of the image is lost or damaged which needs an image restoration. A Prior knowledge of the image may not be available for restoring the image, which demands for a knowledge derivation from the image itself. Restoring the lost portions of the image based on the knowledge obtained from the image area surrounding the lost area is called as Digital Image Inpainting. The information content in the lost area could contain structural information like edges or textural information like repeating patterns. This knowledge is derived from the boundary area surrounding the lost area. Based on this, the lost area is restored by looking at similar information in the same image. Experimentation have been done on various images and observed that the algorithm restores the image in a visually plausible way. © 2013 Springer-Verlag.

More »»

2012

P. Satishkumar, Dr. Padmavathi S., and Krishnan, B. Rohit, “Fabric Defect Detection Using Graylevel Co-Occurrence Matrices (GLCM)”, National Conference on Emerging Trends in Computer Applications and Management (NCETCAM’12. 2012.

2012

K. Kannan, Arunkumar, C., and Dr. Padmavathi S., “Image Recovery in a Contactless Finger Print Image”, National Conference On Simulations In Computing Nexus (NCSCN’12). 2012.

2012

Dr. Padmavathi S. and B. Lakshmi, P., “Wavelet based Digital Image Inpainting”, International Conference On Recent Trends In Computer Science And Engineering ICRTCSE – 2012. p. 26, 2012.

2012

J. Kandasamy and Dr. Padmavathi S., “Structural Information of images using DCT”, International Conference On Recent Trends In Computer Science And Engineering ICRTCSE – 2012. p. 25, 2012.

2012

S. Suganya and Dr. Padmavathi S., “Inpainting using Laplacian Pyramid”, International Conference On Recent Trends In Computer Science And Engineering ICRTCSE – 2012. p. 31, 2012.

2012

Dr. Padmavathi S. and Archana, N., “Hierarchical TV Inpainting”, International Conference On Recent Trends In Computer Science And Engineering ICRTCSE – 2012. p. 37, 2012.

2012

Dr. Padmavathi S., Satishkumar, P., and Krishnan, B. Rohit, “Fabric Defect Detection Using Statistical Texture Analysis”, International Conference on Computer Applications ICCA2012. pp. 69 - 73, 2012.

2012

Dr. Padmavathi S., Rajalaxmi, C., and Dr. Soman K. P., “Texel identification using K-means clustering method”, Advances in Intelligent and Soft Computing, vol. 167 AISC. New Delhi, pp. 285-294, 2012.[Abstract]


Identifying the smallest portion of the image that represents the entire image is a basic need for its efficient storage. Texture can be defined as a pattern that is repeated in a specific manner. The basic pattern that is repeated is called as Texel(Texture Element). This paper describes a method of extracting a Texel from the given textured image using K means clustering algorithm and validating it with the entire image. The number of gray levels in an image is reduced using a linear transformation function. The image is then divided in to sub windows of certain size. These sub windows are clustered together using K-means algorithm. Finally a heuristic algorithm is applied on the cluster labels to identify the Texel, which results in more than one candidate for Texel. The best among them is then chosen based on its similarity with the overall image. The similarity between the Texel and the image is calculated based on then Normalized Gray level co-occurrence matrix in the maximum gradient direction. Experiments are conducted on various texture images for various block sizes and the results are summarized. © 2012 Springer-Verlag GmbH.

More »»

2012

R. Aarthi, Chinnaswamy, A., and Dr. Padmavathi S., “A Survey of Different Stages for Monitoring Traffic Rule Violation”, Communications in Computer and Information Science, vol. 270 CCIS. Vellore, pp. 566-573, 2012.[Abstract]


A traffic surveillance system is a controlled system that helps to monitor and regulate the traffic. In this paper, a method for extracting the license number of the vehicle that is exceeding the speed limit is proposed. A Study is conducted by covering various stages of monitoring system such as vehicle detection in the video, tracking the vehicle for speed calculation and extracting the vehicle number in the number plate that can be used in places with high public vicinity. © 2012 Springer-Verlag.

More »»

2012

R. K. Shangeetha., Valliammai., V., and Dr. Padmavathi S., “Computer vision based approach for Indian sign language character recognition”, 2012 International Conference on Machine Vision and Image Processing, MVIP 2012. Coimbatore, Tamil Nadu, pp. 181-184, 2012.[Abstract]


Deaf and dumb people communicate among themselves using sign languages, but they find it difficult to expose themselves to the outside world. This paper proposes a method to convert the Indian Sign Language (ISL) hand gestures into appropriate text message. In this paper the hand gestures corresponding to ISL English alphabets are captured through a webcam. In the captured frames the hand is segmented and the state of fingers is used to recognize the alphabet. The features such as angle made between fingers, number of fingers that are fully opened, fully closed or semi closed and identification of each finger are used for recognition. Experimentation done for single hand alphabets and the results are summarised. © 2012 IEEE.

More »»

2010

R. Aarthi, Dr. Padmavathi S., and Amudha J., “Vehicle detection in static images using color and corner map”, ITC 2010 - 2010 International Conference on Recent Trends in Information, Telecommunication, and Computing. Kochi, Kerala, pp. 244-246, 2010.[Abstract]


This paper presents an approach to identify the vehicle in the static images using color and corner map. The detection of vehicles in a traffic scene can address wide range of traffic problems. Here an attempt has been made to reduce the search time to find the possible vehicle candidates thereby reducing the computation time without a full search. A color transformation is used to project all the colors of input pixels to a new feature space such that vehicle pixels can be easily distinguished from non-vehicle ones. Bayesian classifier is adopted for verifying the vehicle pixels from the background. Corner map is used for removing the false detections and to verify the vehicle candidates. © 2010 IEEE.

More »»

Publication Type: Conference Paper

Year of Publication Title

2020

Sujee R. and Dr. Padmavathi S., “Fast Texture Classification using Gradient Histogram Method”, in 2020 6th International Conference on Advanced Computing and Communication Systems (ICACCS), 2020.[Abstract]


Classification refers to a physical object as being specified in a set of predefined categories. The goal in texture classification is to provide an unknown sample image for a set of known texture classes. It involves deciding which category of the texture of a painted image. Texture classification is a popular technique used in Image Processing Fields. Its applications includes classification from satellite images in types of land use, automated paint inspection for quality check, automated inspection of defects in the textile industry. In this paper texture classification is done using the gray level co-occurrence matrix. The gradient angle is used to obtain the structural component of the texture. Instead of finding the GLCM for all the angles, in this paper the GLCM of the maximum orientation is used to classify the textures. As a result the computational time and complexity have drastically reduced. Experimental analysis was performed by changing the parameters of the co-occurrence matrix and the gradient angle.

More »»

2018

Sujee R. and Dr. Padmavathi S., “Pyramid-based Image Interpolation”, in 2018 International Conference on Computer Communication and Informatics (ICCCI), 2018.[Abstract]


A technique for better reconstruction of a distorted region in an image using Pyramid-based image interpolation is presented in this paper. The central idea is to construct the image pyramid, so that the apex of the pyramid has a minimized distorted region. The reconstruction of the original image starts from the apex of the pyramid. Each time, the pixels in the distorted region are recovered using bilinear interpolation technique. Since the distorted pixels in the image at the apex of the pyramid have maximal undistorted neighbors, the accuracy of reconstruction is enhanced. Thus the bottom-up approach proposed by this paper results in improved image reconstruction when compared to top-down technique due to the above mentioned higher availability of un distorted pixels in the neighborhood of a distorted pixel.

More »»

2017

V. K and Dr. Padmavathi S., “Facial Parts Detection Using Viola Jones Algorithm”, in 4th International Conference on Advanced Computing and Communication Systems, 2017.

2017

S. Sathya, Joshi, S., and Dr. Padmavathi S., “Classification of breast cancer dataset by different classification algorithms”, in 2017 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017, 2017.[Abstract]


The experimental results show that the classification result with the decision trees algorithm come up over the other classifier. The decision tree algorithm creates a predictive model that predicts the state of the affected tissue by learning simple decision rules inferred while learning.

More »»

2017

M. Muthugnanambika and Dr. Padmavathi S., “Feature Detection for Color Images using SURF”, in 2017 4th International Conference on Advanced Computing and Communication Systems, ICACCS 2017, 2017.[Abstract]


The object recognition and classification is a research problem in the field of computer vision. The computers are trained to automatically identify various objects present in a scene based on various features extracted from it. These features should be the unique ones that will differentiate one object from the other. In this paper, SURF features are extracted from the color image and combined to detect a color object. Based on the experimental results we derive an efficient way to detect the SURF features.

More »»

2017

M. Nehru and Dr. Padmavathi S., “Illumination Invariant Face Detection using Viola Jones Algorithm”, in 2017 4th International Conference on Advanced Computing and Communication Systems (ICACCS), 2017.[Abstract]


In the recent days, there has been a wide advancement in human computing systems. It always remains a challenge to make the computer system behave like how a human senses things. Computer Vision has been a pioneer in making things more automated and better for humans. This paper presents a study based approach for detecting human faces using the Viola Jones algorithm. We train our computer to automatically identify the human faces from the given images irrespective of the illumination conditions. Based on the experimental results we have discussed about the Viola-Jones Cascade Object Detector which uses various filters and the features to detect the various parts of the face.

More »»

2016

S. Gopal and Dr. Padmavathi S., “Speaker verification on English Language using phonemes”, in 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT), 2016.

2016

Dr. Padmavathi S. and Krishnan, S., “Feature Ranking Procedure for Automatic Feature Extraction”, in International conference on Signal Processing, Communication, Power and Embedded System (SCOPES)-2016, 2016.[Abstract]


Classifier allows the user to classify between different classes based on the features acquired. The goals and applications of different classifiers are different. As the feature selection is one of the important criteria. In this paper we introduce a method of ranking the features of one class with respect to another and it tells the user that in the training set which feature has higher ranking among the other. So this method tells which feature is insignificant in certain classes and it can be ruled out. The classification can be made so easily as for some cases, certain features creates confusion in the classifier and wrong interpretations are also occurs. In the training set, if a new data is given as input and this method able to tell the user that the features has a variation with respect to training data set and the feature ranking is calculated. This method automatically ranks the feature and feature selection can be made easier. So we can able to interpret from the significant and insignificant features.

More »»
PDF iconfeature-ranking-procedure-for-automatic-feature-extraction.pdf

2016

Dr. Padmavathi S. and .K, S., “Performance of SVM Classifier For Image Based Soil Classification”, in International conference on Signal Processing, Communication, Power and Embedded System (SCOPES)-2016, 2016.

2016

Dr. Padmavathi S. and M., M., “Performance Analysis of Different Classifiers for Diabetes Classification”, in De Gruyter Digital Library, AET , 2016.

2009

Dr. Padmavathi S., P, I., T, N., D, S., A, S., and S, S., “Audio Steganography”, in National Conference on Cryptography and Network Security , 2009.

Publication Type: Journal Article

Year of Publication Title

2019

K. SA, B.A. Sabarish, and Dr. Padmavathi S., “ Adaptive hybrid image defogging for enhancing foggy images”, Journal of Engineering Science and Technology , vol. 14, no. 6, pp. 3679-3690, 2019.[Abstract]


Images and video captured using camera systems can be seriously degraded by the effect of weather conditions such as fog and haze. Image restoration of true scenes from foggy weather conditions can make a significant difference in many computer vision algorithms such as tracking, surveillance and detection. The main aim of this paper is to develop an Adaptive Hybrid Image Defogging (AHID) algorithm that helps in image restoration with better quality for defogging images under high foggy environments. Combined restoration algorithm consists of image enhancement techniques and multi-level fusionbased defogging algorithms. The adaptive hybrid algorithm consists of many image enhancement techniques with a Dark Channel Prior (DCP) Algorithm to estimate the amount of fog present in the images and atmospheric light as well. The fusion-based defogging algorithm will reduce the remaining artefacts present in the hazy image model. Experiments were conducted with various climatic conditions and the results are summarized in the paper.

More »»

2019

M. K. and Dr. Padmavathi S., “Wild animal detection and recognition from aerial videos using computer vision technique”, International Journal of Emerging Trends in Engineering Research, vol. 7, no. 5, pp. 21-24, 2019.[Abstract]


<p>This paper points to address animal movement detection andtallying with assistance of airborne videos with the help ofglobal pixel from the wide motion recordings. From the aerialvideos, through the movement in the background motion andPIXEL VELOCITY DETECTION segmentation images willbe extracted. Through applying threshold, negative are beingeliminated. This paper mainly focuses on animal detectionfollowing on animal tracking. This Jobs taken after on byeither physically or by in spite of the fact that kept an eye onflying machine which are exceptionally moderate, requiresmanual control and time consuming too. Here we are mainlyfocusing with object spotting and tracking from aerialrecordings and images that can prove viable for wildlifeconservation .</p>

More »»

2019

Anupa Vijai, Dr. Padmavathi S., and Dr. Venkataraman D., “Cloud and Shadow Identification from Aerial Images”, International Journal of Innovative Technology and Exploring Engineering (IJITEE), vol. 8, no. 7, 2019.[Abstract]


Clouds and shadows pose severe problems in discernment of the scene and identification of objects in aerial photography. The changes in illumination,ensued by the presence of cloud and the shadow,aresome of the reasons that lead to ambiguity, while carrying out image segmentation leading to detection of targeted objects. Conventional methods are efficient in detecting thick clouds in contrastive background, but perform poorly in the perception of thin clouds, multiple clouds and their shadows. Reference images for the input are needed in most cases, and separate algorithms are pursued, to identify clouds and shadows in an image, which might not be feasible in all scenarios. Techniques used in this paperto detect cloud and shadows,obviating the need for reference images, are image enhancement, analysis of color histogram of input images, adoption of automatic thresholding and mathematical morphology on the input image. The proposed algorithm,was found to be fast,and experimented on various images that contained multiple white cloud clusters of different shapes, thickness and their shadows. The algorithmwas validated with an accuracy of 94.6% and 87.2% for identification of clouds and shadows, respectively.

More »»

2019

A. R. Kommareddy, Polisetty, S. A., Kurra, C. S., Dr. Padmavathi S., and Pokuri, M. C., “Image based identification of leaf crumple and leaf spot diseases in cotton plant”, International Journal of Recent Technology and Engineering, vol. 8, pp. 345-348, 2019.[Abstract]


Identification of plant diseases based on images derived from computer vision is a major requirement for smart agriculture. Conventional algorithms warrant large dataset for better accuracy. They perform well with large variation in color or explicit probes on a specific disease. This paper considers 4 major diseases of cotton plants with a combination of images with and without color variation. This paper adapted image processing algorithms to extract precise features for classification, highly preferred and apt, when the dataset sizes are limited. Verification results of the proposed method validate its rationale and viability.

More »»

2017

R. Hiralal and Dr. Padmavathi S., “Analysis of Variant Pose Face Detection Using Viola Jones Algorithm”, Jour of Adv Research in Dynamical & Control Systems, pp. 362-366, 2017.

2017

A. K.P and Dr. Padmavathi S., “Supervised Algorithm Based Automatic Bill Classification and Prediction”, International Journal of Engineering and Technology , p. 2837 to2844, 2017.

2017

Dr. Padmavathi S. and Sathiya, R. R., “A relative exploration of unsupervised learning techniques for public conveyance”, International Journal of Pure and Applied Mathematics Open Access, vol. 117, no. 9, pp. 181-185, 2017.

2016

M. Divya and Dr. Padmavathi S., “Identification of the movements of human in a video”, International Journal of Control Theory and Applications, vol. 9, pp. 1119-1123, 2016.[Abstract]


Automatic video surveillance is used for monitoring the behavior of people from distance. Identifying human movement is a major task involved in the process. In this paper the movements of human in a video is identified by using the Global GIST feature. This feature is used to track the corner of the moving body in each frame. The results for various videos involving single or two persons are summarized. © International Science Press. More »»

2016

Dr. Padmavathi S., Naveen, C. R., and V. Kumari, A., “Vision based Vehicle Counting for Traffic Congestion Analysis during Night Time”, Indian Journal of Science and Technology, vol. 9, 2016.[Abstract]


Background/Objectives: To create an automated system that controls the traffic signals effectively based on the instantaneous calculation of traffic congestion during the given time using image processing techniques. Methods/ Statistical Analysis: Vision based Congestion analysis is done based on the vehicles counted from the camera fixed on the signal post. In this paper, the vehicles are detected based on head lights and counted as two wheelers or four wheelers. The congestion is categorized into light, medium and heavy based on this count. Findings: The headlights are separated from the illuminated bright spots by considering its circular and elliptical nature. The accuracy of identifying four wheelers depend on the pairing of the head lights. The existing pairing algorithm fails when one head light is hidden by other vehicles. In this paper, a simple pairing algorithm based on the spatial adjacency is experimented. This had less accuracy due to pairing of two wheeler head lights with that of four wheelers. The problem is alleviated by considering a varying scale factor proportional to the perspective projection of the vehicles in the line of sight. The accuracy of counting increased to 98%, where the drop is due to non-elliptical blobs of head lights that were not detected. Improvements: To guarantee the robust performance of the system, particularly the accuracy and the real-time processing speed. Limitation: The presence of fog lights in modern 4 wheelers are detected as separate cars which reduces the accuracy. The area of improvement will be to consider them as fog lights of the same car and not to mark them as a separate 4 wheelers. More »»

2016

Shanmuga Priya S. and Dr. Padmavathi S., “Comparative analysis of classification algorithms for predicting the advertisements on webpages”, Asian Journal of Information Technology, vol. 15, no. 4, pp. 738-742, 2016.[Abstract]


The fast growth of the Internet has completely changed the way people using computers. In the current scenario, people are more exposed to media and internet has led to the creation of advertisement which can reach users and it has become the ultimate for most business to enhance their profit. More and more ads are being sold on a single-impression basis as opposed to bulk purchases. Identifying whether an image belongs to advertisement or not is of interest to many internet users. This study analyses the performance of probabilistic, tree based and rule based classifier for this classification. Their performances under various conditions are summarized. © Medwell Journals, 2016.

More »»

2016

Dr. Padmavathi S. and Abirami, G., “Detection of abrupt transitions in night time video for illumination enhancement”, Advances in Intelligent Systems and Computing, vol. 397, pp. 809-817, 2016.[Abstract]


A large number of security-related problems could be addressed by night time video surveillance. This has additional challenges of handling nonuniformly illuminated areas in the frame as compared to day time videos. The presence of vehicle lights degrades the existing background extraction process. An intensity- based shot boundary detection technique is applied for the night time videos in this paper. This algorithm is used to identify the abrupt transition frames that are caused by the vehicle lights or moving lights. The frames occuring between such detected frames could be reliably used for background extraction and night time video enhancement. The algorithm is tested on few real-time videos and their results are provided. © Springer India 2016.

More »»

2015

D. Swaminathan, Kiruthika, S., Nivin, A. A. L., and Dr. Padmavathi S., “Video Based Indian Sign Language Recognition System for Single and Double Handed Gestures with Unique Motion Trace as Feature”, International Journal of Tomography & Simulation™, vol. 28, pp. 71–88, 2015.[Abstract]


Gestures or Signs are the means through which audibly challenged people communicate with each other. Sign Language Recognition Systems computerize the job of a sign language translator. Our SLR system is built using powerful Image processing techniques. The system architecture involves techniques for skin color segmentation, Motion-Trace feature extraction and DTW Classification. Our proposed system takes as input a video of the gesture and outputs the text corresponding to the gesture performed. Gestures and signs are used interchangeably used throughout the paper. The system has an overall accuracy of 74.14%.

More »»

2014

Dr. Padmavathi S. and Saradha, S., “Study on Braille Input Output Devices”, International Journal of Engineering Research and Applications, vol. 4, no. 4, pp. 88-93, 2014.

2014

Dr. Padmavathi S. and K. Kumar, A., “A Survey on Algorithms of Shadow Removal in Vehicle Detection”, International Journal of Computer Technology & Applications IJCTA, vol. 5, no. 2, pp. 518 - 521, 2014.

2014

K. Gunasekaran and Dr. Padmavathi S., “Night Time Vehicle Detection for Real Time Traffic Monitoring Systems: A Review”, International Journal of Computer Technology & Applications IJCTA, vol. 5, pp. 451 - 456, 2014.

2014

M. R. Priyadharshini and Dr. Padmavathi S., “Survey on Vehicle Detection techniques”, International Journal of Engineering Research & Technology (IJERT), , vol. 3, no. 3, pp. 420 - 423, 2014.

2014

Dr. Padmavathi S. and Sreenath, S. P., “Literature Survey on Gesture Classification Techniques”, International Journal of Engineering Research & Technology (IJERT), vol. 3, no. 4, pp. 990 - 992, 2014.

2014

Dr. Padmavathi S. and Divya, S., “Survey on Tracking Algorithms”, International Journal of Engineering Research & Technology (IJERT), vol. 3, no. 2, pp. 830 - 834, 2014.

2014

Dr. Padmavathi S., Kiruthika, S., and Kumar, P. I. Navin, “Survey on Hand Gesture Recognition”, International Journal of Engineering Research & Technology (IJERT), vol. 3, no. 2, pp. 943 - 946, 2014.

2014

Dr. Padmavathi S. and , “Face Tracking in Video by using Kalman filter”, International Journal of Engineering Research and Applications, vol. 4, no. 6, pp. 54 - 58, 2014.

2014

Dr. Padmavathi S. and , “A survey on vision based fire detection in videos”, International Journal of Engineering Research and Applications, vol. 4, pp. 85 - 88, 2014.

2014

V. Nivedita, Dr. Padmavathi S., Sankari, G., RaamPrashanth, N. S., and , “Economic Printing Of Braille Documents”, International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS), vol. 2, pp. 170-173, 2014.

2014

S. Divya, Kiruthika, S., Anton, A. L. Nivin, and Dr. Padmavathi S., “Segmentation, Tracking And Feature Extraction For Indian Sign Language Recognition”, International Journal on Computational Sciences & Applications (IJCSA), vol. 4, pp. 57 - 72, 2014.

2014

Dr. Padmavathi S. and Soman, K. P., “Laplacian Pyramid based Hierarchical Image Inpainting”, Advances in Image and Video Processing, vol. 2, pp. 09–22, 2014.[Abstract]


There are many real world scenarios where a portion of the image is damaged or lost. Restoring such an image without prior knowledge or a reference image is a difficult task. Image inpainting is a method that focuses on reconstructing the damaged or missing portion of images based on the information available from undamaged areas of the same image. The existing methods fill the missing area from the boundary. Their performance varies while reconstructing the structure and texture present in the image and majorly fails for larger inpainting area. This paper attempts to segregate the structure and texture using Laplacian Pyramid and inpaint them separately using a top down approach. The images are inpainted from the lowest spatial resolution using Exemplar based image synthesis. The results are updated before moving to the higher resolution levels. This multi resolution process ensures the coarser details being filled before the finer details. The structure propagation is better since it is handled separately. The top down approach alleviates the traditional boundary based filling and breaks the single large sized inpainting region into many smaller sized ones as we move down the pyramid. Different types of images have been experimented and the results are summarized.

More »»

2014

M. Niranjan, Ajtih, J., and Dr. Padmavathi S., “Dynamic Indian Sign Language Character Recognition: Using HOG Descriptor and a Customized Neural Network”, International Journal of Imaging and Robotics™, vol. 14, pp. 35–46, 2014.[Abstract]


Communication is the exchange of thoughts, messages, or information, by speech, visual signals, writing, or behaviour. Deaf and dumb people communicate among themselves using sign languages, but they find it difficult to expose themselves to the outside world. This paper proposes a method for recognizing Indian sign language (ISL) Two hand characters given as input by the user in the form of hand gestures. There are 18 ISL characters which are shown using two hands. Unlike the conventional method, this method does not require any additional hardware and makes the user comfortable. The system takes input at real time through a webcam integrated in the laptop. The hand region is separated out from the background using skin segmentation and motion segmentation. Since the segregation of overlapping hands is difficult, two hand characters are identified using HOG features. A back propagation neural network is used as the learning algorithm to make the system adaptable for different users. The system has been tested for several people of varying skin complexions, in several environments and was found to have accuracy of about 90%. The accuracy mainly dropped due to the illumination of the environment and occlusion of hands involved in two hand gestures.

More »»

2013

Dr. Padmavathi S., S, S. M., and V, V., “Indian Sign Language Character Recognition using Neural Networks”, IJCA Special Issue on Recent Trends in Pattern Recognition and Image Analysis, vol. RTPRIA, pp. 40-45, 2013.[Abstract]


Deaf and dumb people communicate among themselves using sign languages, but they find it difficult to expose themselves to the outside world. This paper proposes a method to convert the Indian Sign Language (ISL) hand gestures into appropriate text message. In this paper the hand gestures corresponding to ISL English alphabets are captured through a webcam. In the captured frames the hand is segmented and the neural network is used to recognize the alphabet. The features such as angle made between fingers, number of fingers that are fully opened, fully closed or semi closed and identification of each finger are used as input to the neural network. Experimentation done for single hand alphabets and the results are summarized.

More »»

2013

Dr. Padmavathi S., .S.Saipreethy, M., and .Valliammai, V., “Indian Sign Language Character Recognition”, pp. 40 - 45, 2013.

2013

Dr. Padmavathi S., Prem, P., and Praveenn, D., “Locating Fabric Defects Using Gabor Filters”, International Research Engineering Journal of Scientific & Technology (IJSRET), vol. 2, no. 8, pp. 472 - 478, 2013.

2013

Dr. Padmavathi S., S Reddy, S., Meenakshy, D., and , “Conversion of Braille to Text in English, Hindi and Tamil Languages”, International Journal of Computer Science, Engineering and Applications (IJCSEA), vol. 3, pp. 19-32, 2013.[Abstract]


The Braille system has been used by the visually impaired for reading and writing. Due to limited availability of the Braille text books an efficient usage of the books becomes a necessity. This paper proposes a method to convert a scanned Braille document to text which can be read out to many through the computer. The Braille documents are pre processed to enhance the dots and reduce the noise. The Braille cells are segmented and the dots from each cell is extracted and converted in to a number sequence. These are mapped to the appropriate alphabets of the language. The converted text is spoken out through a speech synthesizer. The paper also provides a mechanism to type the Braille characters through the number pad of the keyboard. The typed Braille character is mapped to the alphabet and spoken out. The Braille cell has a standard representation but the mapping differs for each language. In this paper mapping of English, Hindi and Tamil are considered.

More »»

2013

K. S. Karthik and Dr. Padmavathi S., “Indian Sign Language Gesture Segmentation Using Active Contour”, IJECCE, vol. 4, pp. 761–766, 2013.

2012

Dr. Padmavathi S., Priyalakshmi, B., and Dr. Soman K. P., “Hirarchical Digital Image Inpainting Using Wavelets”, Signal & Image Processing:An International Journal (SIPIJ), vol. 3, no. 4, pp. 85-93, 2012.[Abstract]


Inpainting is the technique of reconstructing unknown or damaged portions of an image in a visually plausible way. Inpainting algorithm automatically fills the damaged region in an image using the information available in undamaged region. Propagation of structure and texture information becomes a challenge as the size of damaged area increases. In this paper, a hierarchical inpainting algorithm using wavelets is proposed. The hierarchical method tries to keep the mask size smaller while wavelets help in handling the high pass structure information and low pass texture information separately. The performance of the proposed algorithm is tested using different factors. The results of our algorithm are compared with existing methods such as interpolation, diffusion and exemplar techniques.

More »»

2012

Dr. Padmavathi S. and Dr. Soman K. P., “A Hierarchical Search Space Refinement and filling for Exemplar based Image Inpainting”, International Journal of Computer Applications, vol. 52, pp. 31-37, 2012.[Abstract]


There are many real world scenarios where a portion of the image is damaged or lost. Restoring such an image without prior knowledge or a reference image is a difficult task. Image inpainting is a method that focuses on reconstructing the damaged or missing portion of images based on the information available from undamaged areas of the same image. The existing methods fill the missing area from the boundary. Their performance varies while reconstructing structures and textures and many of them restrict the size of the area to be inpainted. In this paper exemplar based inpainting is adopted in a hierarchical framework. A hierarchical search space refinement and hierarchical filling are proposed in this paper which increases the accuracy and handles the extra cost due to multi resolution processing in a better way. The former tries to select an exemplar suitable at all resolution levels restricting the search space from the lower resolution level. The later fills the region at lower resolution level whose results are taken to the higher levels. This makes the non boundary pixels known in the higher resolution level which in turn helps in search space refinement while increasing accuracy.

More »»

2012

Dr. Padmavathi S., Archana, N., and Dr. Soman K. P., “Hierarchical Approach for Total Variation Digital Image Inpainting”, International Journal of Computer Science, Engineering and Applications (IJCSEA), vol. 2, no. 3, pp. 173 - 182, 2012.[Abstract]


The art of recovering an image from damage in an undetectable form is known as inpainting. The manual work of inpainting is most often a very time consuming process. Due to digitalization of this technique, it is automatic and faster. In this paper, after the user selects the regions to be reconstructed, the algorithm automatically reconstruct the lost regions with the help of the information surrounding them. The existing methods perform very well when the region to be reconstructed is very small, but fails in proper reconstruction as the area increases. This paper describes a Hierarchical method by which the area to be inpainted is reduced in multiple levels and Total Variation(TV) method is used to inpaint in each level. This algorithm gives better performance when compared with other existing algorithms such as nearest neighbor interpolation, Inpainting through Blurring and Sobolev Inpainting.

More »»

2012

Dr. Padmavathi S. and Dr. Soman K. P., “Comparative Analysis of Structure and Texture based Image Inpainting Techniques”, International Journal of Electronics and Computer Science Engineering,(IJECSE) Volume, vol. 1, pp. 1062 - 1069, 2012.

Publication Type: Book Chapter

Year of Publication Title

2019

V. Subhashree and Dr. Padmavathi S., “Estimation of parameters to model a fabric in a way to identify defects”, in Lecture Notes in Computational Vision and Biomechanics, vol. 30, Springer Netherlands, 2019, pp. 1251-1260.[Abstract]


Fabric defect detection is a quality check process which can locate and identify defects caused during the production process in the textile industry. Automated defect identification system uses computer vision and pattern recognition techniques whose performance depends majorly on the quality and quantity of the input dataset. A wide range of parameters is considered for decision process which compromises the accuracy of the system. This paper aims to estimate suitable parameters for the defect-free fabric which can be used by traditional methods to identify the defects in an efficient way. Hough-transform-based method is proposed to identify the parameters and the algorithm is experimented on various fabrics. The proposed method gives promising results when the horizontal and vertical threads are evident in the image. © Springer Nature Switzerland AG 2019.

More »»

2018

A. Sarkar and Dr. Padmavathi S., “Image Pyramid for Automatic Segmentation of Fabric Defects”, in Lecture Notes in Computational Vision and Biomechanics,, vol. 28, 2018, pp. 569-578.[Abstract]


Automatic fabric detection is required by the textile industries to improve their quality. For extraction of defective fabric areas, process of segmentation is needed to&nbsp;distinguish&nbsp;the defective region from the background. This paper investigates a method to construct image pyramid by Gaussian method&nbsp;wherein&nbsp;the images are decomposed into multiple levels. Noises are removed and features are extracted for fifteen different defects. Various levels were analyzed and the best level required for proper segmentation is identified for each defect. Region based watershed segmentation and edge based Sobel edge segmentation were experimented on multiple levels. The base level and best level of all decomposed images were compared for all fabric defects investigated.

More »»