Lekha S. Nair currently serves as an Assistant Professor (Senior Grade) at the Department of Information Technology at Amrita School of Engineering, Amritapuri. She pursued her M. Tech. in Computer Science with specialization in Digital Image Computing, University of Kerala and qualified UGC NET and currently pursuing her doctoral studies. She has 12 years of academic experience.
Publications
| Year of Publication | Title |
|---|---|
|
2018 |
C. A. Ancy and Lekha S. Nair, “Tumour Classification in Graph-Cut Segmented Mammograms Using GLCM Features-Fed SVM”, in Intelligent Engineering Informatics, Advances in Intelligent Systems and Computing, Singapore, 2018.[Abstract] Mammograms are customarily employed as one of the reliable computer-aided detection (CAD) techniques. We propose an efficient modified graph-cut (GC) segmented, grey-level co-occurrence matrix (GLCM)-based support vector machine (SVM) technique, for classification of tumour. In this work, SVM classification was carried out in single-view mammograms, subsequent to preprocessing, GC segmentation and GLCM feature extraction. Segmentation of pectoral muscles was done first, followed by segmentation of tumour, using kernel space mapped normalized GCs. We believe this process is the first of its kind used in mammograms. A suitably large number of features were extracted from GLCM, using Haralick method, which in turn increased the training efficiency. The proposed method was tested on 322 different mammograms from Mammographic Image Analysis Society (MIAS) and hence successfully verified to provide efficient results. High accuracy rates were achieved by combining best methods at each stage of diagnosis. More »» |
|
2018 |
A. Unni, Eg, N., Vinod, S., and Lekha S. Nair, “Tumour Detection in Double Threshold Segmented Mammograms Using Optimized GLCM Features fed SVM”, in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), Bangalore, India, 2018.[Abstract] A mammogram is an x-ray image used for early stage breast cancer detection. In this work a novel and efficient method is proposed for tumour detection in mammograms using optimal GLCM features fed to SVM classifier. Optimal feature set from a set of GLCM features are selected using genetic algorithm. The proposed system consists of steps such as pre-processing, threshold segmentation, GLCM feature extraction, optimal feature subset selection using a genetic algorithm and classification using a support vector machine model. After pre-processing the image, binary thresholding is used to remove unwanted objects like high intensity labels from the image and get the required region of interest. Morphological dilation is performed on the segmented region and GLCM features are extracted. Using genetic algorithm, a subset is computed from a given set of features which gives the best classification rate. These features are used for the training of a support vector machine classifier. The trained SVM is used to classify new input images as normal or cancerous. The proposed methodology is tested on the mini MIAS database. More »» |
|
2017 |
C. A. Ancy and Lekha S. Nair, “An efficient CAD for detection of tumour in mammograms using SVM”, in 2017 International Conference on Communication and Signal Processing (ICCSP), Chennai, India, 2017.[Abstract] Breast tumour is one of the prime cancer type in women. Early stage of diagnosis is very important in the treatment of the disease. Mammograms are mostly employed in the Computer Aided Detection (CAD) techniques because a mammogram can often detect tumour in early stage. We propose an efficient Gray Level Co-occurrence Matrix (GLCM) based SVM technique for classifying mammograms. In this paper, classification is done in single view mammograms after performing preprocessing, ROI segmentation, GLCM feature extraction and SVM classification. The proposed method was evaluated on two datasets: University of South Florida Digital Mammography (USFDM) and Mammogram Image Analysis Society (MIAS) database. Early diagnosis and high accuracy rate could be achieved by combining best methods at each stage of diagnosis. From experimental results, it was observed that, the proposed method using GLCM extracted features for classifying tumour and non tumour with SVM classifier could give accurate results. More »» |
|
2017 |
L. Joseph, Pramod, S., and Lekha S. Nair, “Emotion recognition in a social robot for robot-assisted therapy to autistic treatment using deep learning”, in 2017 International Conference on Technological Advancements in Power and Energy ( TAP Energy), Kollam, India, 2017.[Abstract] The Autistic Spectrum Disorder (ASD) is a certain kind of condition characterized by difficulty in social communication, social relationship, and imagination. This condition mainly affects children. The earlier intervention in ASD can help the individual to improve the social skills through Autistic therapies. The robot-assisted therapy is an emerging field in which a special type of robot called social robot is used to interact with ASD individual. These robots have social and communicative skills that can influence the ASD individual. Understanding the emotional state of ASD individual will help in providing appropriate therapy to the individual. This paper discusses emotion recognition technique to be used in a social robot using deep learning techniques. This emotion recognition technique can work in real time to predict the behavior of ASD children. More »» |
|
2015 |
Lekha S. Nair and Joshy, L. M., “An Improved Image Steganography Method with SPIHT and Arithmetic Coding”, in Proceedings of the 3rd International Conference on Frontiers of Intelligent Computing: Theory and Applications (FICTA) 2014, Cham, 2015.[Abstract] The paper proposes a Steganography scheme which focuses on enhancing the embedding efficiency. There are only limited ways on which one can alter the cover image contents. So, for reaching a high embedding capacity, in the proposed method , the data is compressed using SPIHT algorithm and Arithmetic Coding. After which the information is embedded into the cover medium . The proposed method suggests an efficient strategy for hiding an image into a cover image of same size without much distortion and could be retrieved back successfully. The advantage of the system is that the cover medium size is reduced to the same size of the input image where in normal cases it is twice or even more. Also the cover image could be recovered from the original stego-image. More »» |
|
2013 |
H. P, Lekha S. Nair, S.M, A., Unni, R., H, V. Priya, and Poornachandran, P., “Digital Image Forgery Detection on Artificially Blurred Images”, in International Conference on Emerging Trends in Communication, Control, Signal Processing & Computing Applications (C2SPCA), 2013 , Bangalore, India, 2013.[Abstract] In this digital era, lot of information are expressed through images. Various social networking websites, such as Facebook, Twitter, MySpace etc. provides a platform for the users to post up almost any type of picture or photo. However, with the advancement in image editing technologies, many users have become victims of digital forgery as their uploaded images were forged for malicious activities. We have come up with a system which detects image forgery based on edge width analysis and center of gravity concepts. An algorithm based on edge detection is also used to identify the fuzzy edges in the forged digital image. The forged object in the image is highlighted by applying Flood fill algorithm. Different types of image forgeries like Image splicing, Copy-Move image forgery etc. can be detected. This method also reveals multiple forgeries in the same image. The proposed system is capable of detecting digital image forgeries in various image formats efficiently. The results we obtained after the analysis of different images shows that the proposed system is 95% efficient. More »» |
| Year of Publication | Title |
|---|---|
|
2015 |
G. Rajan and Lekha S. Nair, “Offline Signature Forgery Detection using Hough Transform”, International Journal of Applied Engineering Research (Special Issue), vol. 10, pp. 46-49, 2015. |
Related
Sreeja Kochuvila
Asst. Professor
Manishankar S.
Asst. Professor
Peeyush K. P.
Asst. Professor
