Dr. Amudha J. currently serves as Associate Professor at department of Computer Science,Amrita School of Engineering.


Publication Type: Journal Article
Year of Publication Publication Type Title
2016 Journal Article R. Aarthi, Anjana, K. P., and Amudha, J., “Sketch based Image Retrieval using Information Content of Orientation”, Indian Journal of Science and Technology, vol. 9, 2016.[Abstract]

Background/Objectives: This paper presents an image retrieval system using hand drawn sketches of images. Sketch is one of the convenient ways to represent the abstract shape of an object. The main objective is to perform retrieval of images using edge content by prioritizing the blocks based on information. Methods/Statistical Analysis: Entropy based Histogram of Gradients (HOG) method is proposed to prioritize the block. The method helps to pick the candidate blocks dynamically to compare with database images. Findings: The performance of the method has been evaluated using benchmark dataset of Sketch Based Image Retrieval (SBIR) with other methods like Indexable Oriented Chamfer Matching (IOCM), Context Aware Saliency (CAS-IOCM) and Histogram of Gradients (HOG). Comparing to these methods the number of relevant images retrieved is high for our approach.Application/Improvement: Knowledge based block selection method improves the performance of the existing method.

More »»
2013 Journal Article D. Radha, Amudha, J., Ramyasree, P., Ravindran, R., and Snehansh, S., “Detection of unauthorized human entity in surveillance video”, International Journal of Engineering and Technology, vol. 5, pp. 3101-3108, 2013.[Abstract]

With the ever growing need for video surveillance in various fields, it has become very important to automate the entire process in order to save time, cost and achieve accuracy. In this paper we propose a novel and rapid approach to detect unauthorized human entity for the video surveillance system. The approach is based on bottom-up visual attention model using extended Itti Koch saliency model. Our approach includes three modules- Key frame extraction module, Visual attention model module, Human detection module. This approach permits detection and separation of the unauthorized human entity with higher accuracy than the existing Itti Koch saliency model.

More »»
2013 Journal Article J. Amudha, Chadalawada, R. K., Subashini, V., and B. Kumar, B., “Optimised computational visual attention model for robotic cognition”, Advances in Intelligent Systems and Computing, vol. 182 AISC, pp. 249-260, 2013.[Abstract]

The goal of research in computer vision is to impart and improvise the visual intelligence in a machine i.e. to facilitate a machine to see, perceive, and respond in human-like fashion(though with reduced complexity) using multitudinal sensors and actuators. The major challenge in dealing with these kinds of machines is in making them perceive and learn from huge amount of visual information received through their sensors. Mimicking human like visual perception is an area of research that grabs attention of many researchers. To achieve this complex task of visual perception and learning, Visual Attention model is developed. A visual attention model enables the robot to selectively (and autonomously) choose a "behaviourally relevant" segment of visual information for further processing while relative exclusion of others (Visual Attention for Robotic Cognition: A Survey, March 2011).The aim of this paper is to suggest an improvised visual attention model with reduced complexity while determining the potential region of interest in a scenario. © 2013 Springer-Verlag.

More »»
Publication Type: Conference Paper
Year of Publication Publication Type Title
2010 Conference Paper R. Aarthi, Padmavathi, S., and Amudha, J., “Vehicle detection in static images using color and corner map”, in ITC 2010 - 2010 International Conference on Recent Trends in Information, Telecommunication, and Computing, Kochi, Kerala, 2010, pp. 244-246.[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 »»
Faculty Details


Faculty Email: