Qualification: 
Ph.D, MCA
Email: 
p_latha@cb.amrita.edu

Born, brought up and settled as Coimbatorean, Dr. Latha Parameswaran joined the Department of Computer Science and Engineering at the Coimbatore campus of Amrita Vishwa Vidhyapeetham in 1999. She is currently the professor and Chairperson of the Department of Computer Science and Engineering. She was in the software industry for ten years prior to joining Amrita. She completed her Master's Degree from PSG College of Technology and her  Ph. D. from Bharathiar University. Her Ph.D. thesis titled “Digital Watermarking for Image Security” was highly commended by the experts. Her areas of research include Image Processing, Information Retrieval, Image Mining, Information Security and Theoretical Computer Science.

She has published papers in international journals and at conferences where she has won several Best Paper Awards.  She has also authored a chapter in a book published by the Idea Group.

In addition to teaching and serving as Chair of the CSE department, she is currently guiding  Ph. D. research scholars in Amrita, Bharathiar and Anna Universities. She is in the doctoral committee for many Ph. D. scholars in various Universities. She is also a member in Board of Studies at various premier academic institutions in India. She also holds positions in academic council in premier institutions. She is in the faculty recruitment board, faculty appraisal committee, funded project review committee, recommendations for infrastructure setting up committee at various institutions.

She also works on projects funded by DST. Her Special Interests include encouraging more and more women in to work in Engineering, Technology and Computing.  Also she conducts workshops for school children in the classes 8-12 to encourage them to pursue computer science as their field of study. In connection with this she has conducted two conferences on Women in Computing at Amrita Vishwa Vidyapeetham in 2010 and 2013. The next in this series is planned in 2016.

Publications

Publication Type: Conference Paper

Year of Conference Publication Type Title

2017

Conference Paper

Dr. Shyamala C. K., Dr. Shunmuga Velayutham C., and Dr. Latha Parameswaran, “Teaching computational thinking to entry-level undergraduate engineering students at Amrita”, in IEEE Global Engineering Education Conference, EDUCON, 2017, pp. 1731-1734.[Abstract]


This paper is about various aspects of the Computational Thinking and Problem Solving course offered to entry-level undergraduate engineering students across 7 engineering disciplines at Amrita University, India. The various aspects include the motivations for offering the course, aims and objectives of the course, course design as well as the delivery and assessment of the course. The paper also shares the experience of conducting the course to a very large number of students and the lessons learnt during the process. © 2017 IEEE.

More »»

2013

Conference Paper

S. Sruthy, Dr. Latha Parameswaran, and Sasi, A. P., “Image fusion technique using DT-CWT”, in Proceedings - 2013 IEEE International Multi Conference on Automation, Computing, Control, Communication and Compressed Sensing, iMac4s 2013, Kerala, 2013, pp. 160-164.[Abstract]


Image Fusion is the process of combining information of two or more images into a single image which can retain all important features of the all original images. Here the input to fusion involves set of images taken from different modalities of the same scene. Output is a better quality image; which depends on a particular application. The objective of fusion is to generate an image which describes a scene better or even higher than any single image with respect to some relevant properties providing an informative image. These fusion techniques are important in diagnosing and treating cancer in medical fields. This paper focuses on the development of an image fusion method using Dual Tree Complex Wavelet Transform. The results show the proposed algorithm has a better visual quality than the base methods. Also the quality of the fused image has been evaluated using a set of quality metrics. © 2013 IEEE.

More »»

2010

Conference Paper

T. Arathi, Dr. Latha Parameswaran, and Soman, K. P., “A study of reconstruction algorithms in computerized tomographic images”, in Proceedings of the 1st Amrita ACM-W Celebration of Women in Computing in India, A2CWiC'10, Coimbatore, 2010.[Abstract]


Computerized tomography is extensively used in the medical imaging field. It has made a revolutionary impact in diagnostic medicine, helping doctors to view the internal organs of the human body to a very high precision, at the same time ensuring complete safety to the patient. This paper is a study of two such reconstruction algorithms, most commonly used in computerized tomography. They are the filtered backprojection algorithm and the fanbeam projection algorithm respectively. A comparison between the performances of the two methods has been carried out using a set of quality metrics. The experimental results and the conclusions drawn are also included. © 2010 ACM. More »»

Publication Type: Journal Article

Year of Conference Publication Type Title

2016

Journal Article

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


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

More »»

2016

Journal Article

S. Athira, Manjusha, R., and Dr. Latha Parameswaran, “Scene understanding in images”, Advances in Intelligent Systems and Computing, vol. 530, pp. 261-271, 2016.[Abstract]


Scene understanding targets on the automatic identification of thoughts, opinion, emotions, and sentiment of the scene with polarity. The sole aim of scene understanding is to build a system which infer and understand the image or a video just like how humans do. In the paper, we propose two algorithms- Eigenfaces and Bezier Curve based algorithms for scene understanding in images. The work focuses on a group of people and thus, targets to perceive the sentiment of the group. The proposed algorithm consist of three different phases. In the first phase, face detection is performed. In the second phase, sentiment of each person in the image is identified and are combined to identify the overall sentiment in the third phase. Experimental results show Bezier curve approach gives better performance than Eigenfaces approach in recognizing the sentiments in multiple faces. © Springer International Publishing AG 2016. More »»

2015

Journal Article

S. L. Nair, Manjusha, R., and Dr. Latha Parameswaran, “A survey on context based image annotation techniques”, International Journal of Applied Engineering Research, vol. 10, pp. 29845-29856, 2015.[Abstract]


The importance of image acquisition and then analysing them for various purposes is increasing everyday.Image annotation and retrieval is a vital process for analysis of large data. Context based annotation systems labels the images based on the context of the scene and provides accurate results for automatic annotation compared to the earlier Content based systems and thus has become a very important research domain in image processing. Many approaches and representations are proposed and developed for context based image annotation.This paper provides anoverview of some of the important approaches and representations of objects and their relationship used widely for context based image annotation. © Research India Publications.

More »»

2015

Journal Article

C. K. Dinesh Kumar, Manjusha, R., and Dr. Latha Parameswaran, “Comparision of image classification methods on event data”, International Journal of Applied Engineering Research, vol. 10, pp. 29631-29640, 2015.[Abstract]


The aim of this work is to classify images related to social events. With advances in digital image processing, automated classification of event related images over large categories of dataset is possible only if the name of the event is known. The purpose of the paper is to identify different events in a given set of images with the help of visual content. We compare the performance of Global (GIST) as well as Local Descriptors (SIFT) which is helpful in achieving this classification and retrieval of images. The performances of both the approaches are assessed. © Research India Publications.

More »»

2015

Journal Article

K. R. Bindu, Dr. Latha Parameswaran, and Soumya, K. V., “Performance Evaluation of Topic Modelling Algorithms with an application of Q & A Dataset”, International Journal of Applied Engineering Research, vol. 10, pp. 23- 27, 2015.

2015

Journal Article

K. R. Bindu, Nambiar, S. R., Chandran, J., and Dr. Latha Parameswaran, “Performance Evaluation of Algorithms for Expert finding on an Open Email dataset”, International Journal of Applied Engineering Research, vol. 10, pp. 23-27, 2015.

2014

Journal Article

A. T. and Dr. Latha Parameswaran, “Image Reconstruction from 2D stack of MRI/CT to 3D using Shapelets”, International Journal of Engineering and Technology (IJET), vol. 6, pp. 2595 – 2603, 2014.[Abstract]


Image reconstruction is an active research field, due to the increasing need for geometric 3D models in movie industry, games, virtual environments and in medical fields. 3D image reconstruction aims to arrive at the 3D model of an object, from its 2D images taken at different viewing angles. Medical
images are multimodal, which includes MRI, CT scan image, PET and SPECT images. Of these, MRI and CT scan images of an organ when taken, is available as a stack of 2D images, taken at different angles. This 2D stack of images is used to get a 3D view of the organ of interest, to aid doctors in easier diagnosis.
Existing 3D reconstruction techniques are voxel based techniques, which tries to reconstruct the 3D view based on the intensity value stored at each voxel location. These techniques don’t make use of the shape/depth information available in the 2D image stack. In this work, a 3D reconstruction technique for MRI/CT 2D image stack, based on Shapelets has been proposed. Here, the shape/depth information available in each 2D image in the image stack is manipulated to get a 3D reconstruction, which gives a more accurate 3D view of the organ of interest. Experimental results exhibit the efficiency of this proposed technique.

More »»

2013

Journal Article

T. Arathi and Dr. Latha Parameswaran, “Slantlet Transform and Phase Congruency based Image Compression”, International Journal of Computer Applications (IJCA), Proceedings on Amrita International Conference of Women in Computing - 2013, vol. AICWIC, pp. 12-16, 2013.[Abstract]


Image compression is an active area of research with a wide range of applications. Being able to represent an image with lesser number of coefficients, without affecting the image quality has been the prime aim of image compression. In this research, a new image compression technique has been proposed, based on Slantlet Transform and the principle of Phase Congruency. The compressed image quality has been assessed by computing the PSNR values and the compression ratios. Experimentation show highly promising results, in terms of the level of compression and the quality of the fused image.

More »»

2013

Journal Article

A. T. and Dr. Latha Parameswaran, “An Image Fusion Technique Using Slantlet Transform and Phase Congruency for MRI/CT”, International Journal of Biomedical Engineering and Technology, vol. 13, no. 1, pp. 87-103, 2013.[Abstract]


Image fusion aims at maximally making available, the information from two or more input images of the same scene into a single composite image. Medical images are acquired using different modalities, which include MRI, CT scan, PET and SPECT images. Fusing them makes available the information from multiple images into a single composite image, aiding doctors in easier diagnosis. Most existing fusion techniques give more importance to the quality of the fused image, than the computational complexity. In this research, a new image fusion technique addressing computational complexity has been proposed, for combining MRI and CT images. The method has been found to be computationally efficient, in terms of the number of transform domain coefficients participating in the fusion process, without any compromise in the visual quality of the fused image. Experimental results exhibit the efficacy of this proposed technique, both in terms of computational cost and image quality.

More »»

2013

Journal Article

A. T. and Dr. Latha Parameswaran, “A Computationally Efficient Edge Preserving MRI-CT Image Fusion Technique using Complex Wavelet Transform and Phase Congruency Fusion Rule”, European journal of Scientific Research, vol. 112, no. 4, pp. 469-483, 2013.[Abstract]


Efficient fusion of multimodal medical images has been a constant topic of research. A variety of fusion rules have been proposed in the literature, which fuses the information in MRI and CT images of the organs of interest. The prime aim of all these fusion techniques has been to maximally make available the information from both the images in a single composite image. This aids the medical practitioners in their analysis. Most of these existing techniques give more importance to the quality of the fused image, than the computational complexity. Fusing the multimodal images in the transform domain usually involves fusion of all the transform domain coefficients, whose number increases with the increase in the number of multiresolution levels chosen. In this research, we have proposed a fusion technique based on Complex Wavelet Transform and Phase Congruency. This method is computationally efficient, in terms of the number of transform domain coefficients participating in the fusion process and visual quality. The concept of phase congruency makes sure that the edge information in the source images gets preserved in the fused image. It also reduces the number of transform domain coefficients taking part in the fusion process by a huge margin, when compared with the conventional transform domain fusion techniques. An edge preservation quality measure has been used to quantitatively analyze the edge preservation capacity of the proposed technique. The quality of the fused image is analyzed using some existing quality metrics. Experimental results exhibit the efficiency of this proposed technique, in producing a fused image with lesser number of coefficients without compromise on visual quality.

More »»

2010

Journal Article

T. Arathi, Soman, K. P., and Dr. Latha Parameswaran, “Spline Biorthogonal Wavelet Design”, Proceedings of International Conference on Advances in Information and Communication Technologies, Communications in Computer and Information Science, vol. 101, pp. 672-674, 2010.[Abstract]


This paper gives a simple and straightforward method for designing spline based biorthogonal wavelets. Biorthogonal wavelets differ from orthogonal wavelets in that the former has more flexibility in its design. This is because, they enable the design of wavelets which are symmetric and smooth, which is not possible in the case of orthogonal wavelets (except Haar wavelet). However, the compromise made to achieve the symmetry property is that the non-zero coefficients in the analysis and synthesis filters are not the same for biorthogonal wavelets. The existing algorithm for spline biorthogonal wavelet design involves complex formulas, whose proof is also not easily understandable. In this paper, we present a very simple way of constructing spline based biorthogonal wavelets, which results in the same nonzero coefficients for the analysis and synthesis filters. © Springer-Verlag Berlin Heidelberg 2010. More »»

2008

Journal Article

Dr. Latha Parameswaran and Anbumani, K., “Content-based watermarking for image authentication using independent component analysis”, Informatica (Ljubljana), vol. 32, pp. 299-306, 2008.[Abstract]


This paper proposes a novel approach to content-based watermarking for image authentication that is based on Independent Component Analysis (WA). In the scheme proposed here, ICA is applied to blocks of the host image and the resulting mixing matrix represents the features of the image blocks, Frobenius norm of the mixing matrix is adopted as the content-based feature. This is embedded as the watermark in a mid-frequency DCT coefficient of the block. This authentication technique is robust against incidental image processing operations, but detects malicious tampering and correctly locates the tampered regions. More »»

2007

Journal Article

Dr. Latha Parameswaran and K., A., “A Content Based Image Watermarking Scheme Resilient to Geometric Attacks”, International Journal of Computer Science, vol. 2, pp. 70-75, 2007.

2007

Journal Article

Dr. Latha Parameswaran and K., A., “A semi-fragile image watermarking using wavelet inter-coefficient relations”, International Journal of Information Security & Privacy, vol. 1, pp. 61-75, 2007.[Abstract]


Proliferation of multimedia on the Internet has led to the need for developing authentication mechanisms. This article proposes a new blind watermarking scheme based on the contents of the image in the discrete wavelet transform domain for image authentication. The host image is discrete wavelet transformed up to second level. The relationship between neighboring wavelet coefficients in each band of the second level decomposition is considered to construct the content-based watermark. The watermark is embedded in the first level mid frequency band, of the discrete wavelet transformed image. The received image is authenticated by extracting the watermark and determining the level of authenticity. This scheme is capable of tolerating content-preserving modifications and detecting content-changing modifications. Experimental results prove the efficiency of the scheme. More »»

2006

Journal Article

Dr. Latha Parameswaran and K., A., “A robust image watermarking scheme using image moment normalization”, Transactions on Engineering, Computing and Technology, World Enformatika Society, vol. 13, pp. 239-243, 2006.[Abstract]


Multimedia security is an incredibly significant area of concern. A number of papers on robust digital watermarking have been presented, but there are no standards that have been defined so far. Thus multimedia security is still a posing problem. The aim of this paper is to design a robust image-watermarking scheme, which can withstand a different set of attacks. The proposed scheme provides a robust solution integrating image moment normalization, content dependent watermark and discrete wavelet transformation. Moment normalization is useful to recover the watermark even in case of geometrical attacks. Content dependent watermarks are a powerful means of authentication as the data is watermarked with its own features. Discrete wavelet transforms have been used as they describe image features in a better manner. The proposed scheme finds its place in validating identification cards and financial instruments. More »»

Publication Type: Conference Proceedings

Year of Conference Publication Type Title

2014

Conference Proceedings

S. T.P., R., M., and Dr. Latha Parameswaran, “A Novel Method for Vehicle Detection and Speed Estimation in Aerial Images”, International Conference on Signal and Speech Processing (ICSSP-14). pp. 81-88, 2014.

2014

Conference Proceedings

A. T. and Dr. Latha Parameswaran, “A Method for Image Representation Using Slantlet Transform and Phase Congruency”, International Conference on Interdisciplinary Advances in Applied Computing, ICONIAAC. ACM New York, NY, 2014.[Abstract]


Image representation is an active area of research due to its increasing applications in internet, military and defense. Image representation aims at representing an image with lesser number of coefficients than the actual image, without affecting the image quality. It is the first step in image compression. Once the image is represented by using some set of coefficients, it is further encoded using various compression algorithms. This paper proposes an adaptive method for image representation, which uses Slantlet transform and the concept of phase congruency, where the number of coefficients used for image representation depends on the information content in the input image. The efficiency of the proposed method has been assessed by comparing the number of coefficients used to represent the image using the proposed method with that used when Slantlet transform is used for image representation. The image quality is determined by computing the PSNR values and some commonly used existing quality metrics. Experiments carried out show highly promising results, in terms of the reduction in the number of coefficients used for image representation and the good visual quality of the resultant image.

More »»

2013

Conference Proceedings

A. T. and Dr. Latha Parameswaran, “A method for Image representation using Slantlet Transform and Phase Congruency”, Proceedings of ACM National Conference on Intelligent Computing. PSG College of Technology, Coimbatore, 2013.[Abstract]


Image representation is an active area of research due to its increasing applications in internet, military and defense. Image representation aims at representing an image with lesser number of coefficients than the actual image, without affecting the image quality. It is the first step in image compression. Once the image
is represented by using some set of coefficients, it is further encoded using various compression algorithms. This paper proposes an adaptive method for image representation, which uses Slantlet transform and the concept of phase congruency, where the number of coefficients used for image representation depends on the information content in the input image. The efficiency of the proposed method has been assessed by comparing the number of coefficients used to represent the image using the proposed method with that used when Slantlet transform is used for image representation. The image quality is determined by computing the PSNR values and some commonly used existing quality metrics. Experiments carried out show highly promising results, in terms of the reduction in the number of coefficients used for image representation and the good visual quality of the resultant image

More »»

2013

Conference Proceedings

K. Nagrjuna Varma and Dr. Latha Parameswaran, “Email Thread Word Cloud Generator”, Proceedings of Asian Summer School in Information Access (ASSIA 2013). Tsukuba, Japan, 2013.

2013

Conference Proceedings

A. T. and Dr. Latha Parameswaran, “Image representation method based on Complex Wavelet Transform and Phase Congruency, with Automatic Threshold Selection”, International Conference on Biology, Medical Physics, Medical Chemistry, Biochemistry and Biomedical Engineering, BIOMED. Venice, Italy , pp. 19-23, 2013.[Abstract]


Image representation is an active area of research with increasing applications in military and defense. Image representation aims at representing an image with lesser number of coefficients than the actual image, without affecting the image quality. It is the first step in image compression. Once the image is represented by using some set of coefficients, it is further encoded using various compression algorithms. This paper proposes an adaptive method for image representation, which uses Complex Wavelet transform and the concept of phase congruency, where the number of coefficients used for image representation depends on the information content in the input image. The efficiency of the proposed method has been assessed by comparing the number of coefficients used to represent the
image using the proposed method with that used when Complex Wavelet transform is used for image representation. The resultant image quality is determined by computing the PSNR values and Normalized Cross Correlation. Experiments carried out show highly promising results, in terms of the reduction in the number of coefficients used for image representation and the quality of the resultant image.

More »»

2013

Conference Proceedings

K. K. P. and Dr. Latha Parameswaran, “A hybrid method for object identification and event detection in video”, National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG). IEEE Explore, Jodhpur, India, pp. 1-4, 2013.[Abstract]


Video event detection (VED) is a challenging task especially with a large variety of objects in the environment. Even though there exist numerous algorithms for event detection, most of them are unsuitable for a typical consumer purpose. A hybrid method for detecting and identifying the moving objects by their color and spatial information is presented in this paper. In tracking multiple moving objects, the system makes use of motion of changed regions. In this approach, first, the object detector will look for the existence of objects that have already been registered. Then the control is passed on to an event detector which will wait for an event to happen which can be object placement or object removal. The object detector becomes active only if any event is detected. Simple training procedure using a single color camera in HSV color space makes it a consumer application. The proposed model has proved to be robust in various indoor environments and different types of background scenes. The experimental results prove the feasibility of the proposed method.

More »»

2008

Conference Proceedings

Dr. Latha Parameswaran and Rahmad, K., “Image Watermarking for Transaction Tracking and Copyright Protection using PCA”, Proceedings of International Conference on Recent Trends in Computational Science (ICRTCS – 2008). TocH Institute of Science and Technology, Kochi, 2008.

2006

Conference Proceedings

Dr. Latha Parameswaran and K., A., “A semi fragile content-based image watermarking for authentication in spatial domain using discrete cosine transform”, IEEE International Conference on Signal and Image Processing. pp. 14-19, 2006.

2006

Conference Proceedings

Dr. Latha Parameswaran and K., A., “A Content Based Image Watermarking Scheme for Authentication using Quadtrees”, International Conference on Advanced Computing and Communications (ADCOM 2006) . NITK, Surathkal, India, pp. 151-156, 2006.[Abstract]


With the introduction of multimedia, the number of users using images for various purposes has grown enormously. Authentication techniques provide a means of ensuring the integrity of the image. This paper discusses an authentication technique that would generate a watermark based on the features of the image and store it in the image itself. This scheme uses a quadtree structure to generate the watermark. The source image is divided into quadrants up to a desired level and a quadtree is constructed. The mean of the DCT coefficients of each quadrant is computed and stored in the edges of the quadrant. The scheme is also capable of withstanding a set of attacks. Experimental results have shown the effectiveness of the scheme. This scheme can be used to authenticate digital documents such as identity cards, passports, driving licenses where image is the primary data. More »»

2005

Conference Proceedings

Dr. Latha Parameswaran, “Content dependent image signature for authentication using wavelets”, Proceedings of National Conference on Information Security. Karunya University, Coimbatore, India, 2005.

2004

Conference Proceedings

Dr. Latha Parameswaran, “Content-based image authentication scheme”, Proceedings of National Conference on Multimedia Technologies and Applications. Karunya University, Coimbatore, India, pp. 116-131, 2004.

2004

Conference Proceedings

Dr. Latha Parameswaran and K., A., “Image security using message authentication codes”, Proceedings of 4th National Conference on Advanced Computing. PSG College of Technology, Coimbatore, India, 2004.

2004

Conference Proceedings

Dr. Latha Parameswaran and K., A., “Quadtrees-based image authentication”, Proceedings of National Workshop on Cryptology, Cryptology Research Society of India. Amrita Vishwa Vidyapeetham, Kollam, India, 2004.

Publication Type: Book

Year of Conference Publication Type Title

2009

Book

Dr. Latha Parameswaran and Anbumani, K., A content-based watermarking scheme for image authentication using discrete wavelet transform inter-coefficient relations. Information Science Reference, 701 E, Chocolate Avenue, Hershey, PA 17033, USA : IGI Global, 2009, pp. 173-187.[Abstract]


This chapter discusses a content-based authentication technique based on inter-coefficient relationship of Discrete Wavelet Transform (DWT). Watermark is generated from the first level DWT. An image digest (which is a binary string) is generated from the second level DWT. The watermark is embedded in the mid-frequency coefficients of first level DWT as directed by the image digest. Image authentication is done by computing the Completeness of Signature. The proposed scheme is capable of withstanding incidental image processing operations such as compression and identifies any malicious tampering done on the host image. © 2009, IGI Global. More »»
207
PROGRAMS
OFFERED
5
AMRITA
CAMPUSES
15
CONSTITUENT
SCHOOLS
A
GRADE BY
NAAC, MHRD
9th
RANK(INDIA):
NIRF 2017
150+
INTERNATIONAL
PARTNERS