Qualification: 
M.Tech
a_baskar@cb.amrita.edu

Baskar A. currently serves as Assistant Professor at the Department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore Campus. His areas of research include Computer Vision, Video Processing, Image Processing and Machine learning. He completed his B. E. (Computer Science and Engineering) from Sona College of Technology, Salem. He then completed his M. Tech. (Computer Vision and Image Processing) from Amrita Vishwa Vidyapeetham, Coimbatore.

Scopus Author ID: 56511853600
ORCID: 0000-0003-2000-6824

Awards and Recognitions

  1. Distinguished Facilitator Award (Technical) - Inspire - Runner-up - Faculty award by Infosys Technologies, Mysore @ 2017.
  2. Acknowledged by Texas Instruments for the project guidance.
  3. Recognized as AWS Educate Cloud Faculty Ambassador by AWS @2019
  4. Recognized as Intel Software Innovator by Intel @2019
  5. Recognized as AWS Educate Cloud Faculty Ambassador by AWS @2020
  6. Recognized as Intel Software Innovator by Intel @2020

Publications

Publication Type: Journal Article

Year of Publication Title

2021

A. Baskar and P.H, A., “An automatic histogram detection and information extraction from document images”, International Journal of Speech Technology, vol. 24(1), pp. 77–85., 2021.[Abstract]


Histogram is an important data chart that is commonly present in scientific documents. In this paper, an automatic histogram detection and information extraction methodology, based on Hough line detector and Morphological operator, is proposed. The proffered system is comprised of three steps: pre-processing, axis detection, and chart pattern extraction. In the pre-processing step, the RGB image pattern of a histogram is converted into a binary image. Next, in the axis detection step, horizontal axis, vertical axis and title of the histogram are extracted. In this step Hough line detector methodology was applied to detect horizontal and vertical lines in the image patterns. From the set of identified vertical lines, both the endpoints of a line, having the same minimum values of x co-ordinate was considered as a vertical axis. Similarly, from the set of identified horizontal lines, the two endpoints of a line having the same maximum values of y co-ordinate were considered as a horizontal axis. With respect to the dimensions of the horizontal axis and vertical axis, a rectangular region containing horizontal axis values and label, vertical axis values and label and title are extracted. In the final chart pattern extraction step, using morphological operations, the frequency of data present in the histogram was identified. Verification and validation tests of the propounded system yielded promising results, indicative of efficient approach for extraction of histogram information.

More »»

2018

S. A. Kumar and A. Baskar, “Improving the IRIS recognition under different illumination using RETINEX algorithms”, International Journal of Engineering & Technology, vol. 7(3):81-83, 2018.[Abstract]


Iris detection and recognition provides more accurate and secure authentication nowadays. The probability of any two people having the same iris pattern is nearly zero, even the identical twins will not have the same iris pattern. The noise and illumination changes, challenges iris recognition correctness and security in authentication process. The available recent pre-processing techniques for iris detection address different type of noise suppression and removing unwanted information in iris, but still it strives with illumination issues. In this paper, we proposed Retinex algorithm for improving iris detection rate. The proposed work comprises into three steps: First we proposed Retinex algorithm in pre-processing, it works based on reflectance value of image and skips the illumination value in image, subsequently feature extraction uses Gabor filter for iris code generation. In conclusion, distance metrics Hamming distance used for iris recognition the proposed work evaluated MMU iris database under different illumination conditions and provides better results.

More »»

2017

S. Sindhuja and A. Baskar, “An automatic table detection and cell extraction using image morphological operations”, Journal of Advanced Research in Dynamical and Control Systems, vol. 9, no. Special issue 11, pp. 184-193, 2017.[Abstract]


Tables are compact and efficient means for representing information. Automatic table structure extraction is a challenging problem in the field of document layout analysis. In this paper, an automatic table detection and cell extraction using image morphological operations proposed. The proposed system comprises of four distinct steps. Corners and line intersections identification step, which detects the four outer corners and all the inner line intersections using nine structuring elements. Textual elements present in the table may create false corners and line intersections, which affects the identification of cells in a table. The proposed system introduced two methods namely, the intersection operation between structuring elements followed by a projection profile for removing false corners and line intersection in the noise removal step. Finally, cells in a table are identified using connected components. Our proposed system is tested on tables without textual information, tables with textual information, tables with increased line thickness and tables with no rows and column lines under diverse background and various sizes. The result shows our proposed system provides better results. © 2017, Institute of Advanced Scientific Research, Inc. All rights reserved.

More »»

2017

A. Baskar, Kishan, D., and Lingesh, B. V., “A vision system to guide visually challenged to pick up ingredients from rack”, Journal of Advanced Research in Dynamical and Control Systems, vol. 2017, no. Special Issue 11, pp. 27-35, 2017.[Abstract]


Rapid technological advancements provides a plenty of products to help visually impaired people. In this work we propose a Vision system to guide visually challenged to pick up ingredients from rack, which aids a visually impaired to identify an object in self and guide them towards the object with an audio feedback system. Our system which acts as a personal helping hand for the user thus reducing the visually impaired user’s reliance on other people, especially with strangers when in a new environment. The proposed system implemented in three steps. First, Identification of self and detecting object present on self. Followed by in second step, Calibration of self, it calibrates user to an accessible distance from the shelf and to center of the frame. Finally, it guides user towards the recognized object with an audio feedback system. This approach is tested in an ideal environment with varied illumination and we used a shelf with three containers. © 2017, Institute of Advanced Scientific Research, Inc. All rights reserved.

More »»

2015

Dr. Shriram K Vasudevan, Priyadarsini, P. L. K., and A. Baskar, “An intelligent system of content-based image retrieval for crime investigation”, International Journal of Advanced Intelligence Paradigms, vol. 7, no. 3-4, pp. 264–279, 2015.[Abstract]


Crimes in the modern world have been increasing dramatically in proportion with technological growth. In many situations, investigators have a sketch of the criminal, generated from the details given by the eye witnesses. There is a need of a better methodology for identifying the culprits from those images. Nowadays, RAM and memory sizes have become huge and in turn, there is a tremendous increase in the size of the databases. Investigators have huge datasets with details, photographs, images of the criminals or crime scenes and this is the second important consideration. Image search has become highly challenging task in these dense database environments. Accuracy and speed are two important factors for this type of image searches. We propose a compact embedded search engine to search and extract images from these data bases, using a content-based image retrieval (CBIR) algorithm.

More »»

2015

S. M. Thomas and A. Baskar, “Smart pharmacist for visually impaired”, International Journal of Applied Engineering Research, vol. 10, no. 15, pp. 35948-35953, 2015.[Abstract]


Lot of technologies has been emerged to help visually impaired. For example Obstacle detection, assistance in the supermarket, identification and location of people, navigation. In this system we propose an algorithm to assist them to identify the labels on a medicine strip. It uses a mono camera to extract the intended information’s such as tablet name and manufacturing date from medicine strip which will assist visually challenged people for medication. The system consists of three phases: data capture, data processing, and audio output. The data capture component collects scenes containing medicine strip in the form of images. The data processing component works with the proposed algorithms to transform image-based text information into readable text. The audio output component is to inform the blind user by converting it into speech output. This system is tested with bristle type medicine strips and the system gives better results in different cases like different background color, different font size and different layout. © Research India Publications.

More »»

2015

S. T. Maheswari, Unni, A. S., and A. Baskar, “Fire fighting robot using LEGO Mindstorm”, International Journal of Applied Engineering Research, vol. 10, no. 8, pp. 20129-20138, 2015.[Abstract]


Background/Objectives: In this paper a prototype of Fire Fighting Robot (FFR) using LEGO Mindstorm is proposed for disaster management, which has the functionality of quick movement inside a building, detecting obstacles and locating the fire on its way. Simulation of the prototype is accomplished by two modulus Fire detection and message alert. FFR uses the ultrasonic sensor to move around the obstacles and light sensor to find out the fire origin. When the fire is detected it will send messages alert to the people in, building regarding fire disaster and extinguish the fire. Simulation of the robot is tested under various scenarios with different test cases and the result is discussed in result and analysis. Conclusion/Application:The simulation designed is proved to safeguard the human life and property from the fire accident. FFR can be considered as the useful simulation for the real time application. © Research India Publications.

More »»

2014

A. Baskar and R. Babu, U., “Inter-video frame duplication detection using spatial correlation and optical flow algorithms”, International Journal of Tomography and Simulation, vol. 27, no. 3, pp. 84-100, 2014.[Abstract]


The videos produced as evidences in courts, science and business are exceedingly confidential and even a simple amendment done in these videos will have a greater impact on our civilization. To ensure the genuineness of such videos, better methods are needed. In this paper we propose a technique to find inter-frame duplications (a video is tampered by adding frames from different videos) which includes two phases. Phase1 extract the key frames from the given input video and thus reduces the computation time compared to frame by frame comparisons, followed by phase2 which uses spatial Correlation and optical flow algorithm to detect the forgery from the key frames. The experimental results show our algorithm detects forgery efficiently beneath the following circumstances such as: Inserting Duplicate frames at random positions, Inserting duplicate frames throughout the video except the first frame and Inserting only one duplicate frame in the entire video.

More »»

2012

M. D. Dhanya and A. Baskar, “Invisible mouse using 2D-tree based virtual grid and hand gesture recognition”, International Journal of Tomography and Statistics, vol. 19, no. 1, pp. 68-80, 2012.[Abstract]


Invisible Mouse (IM) endeavours the real-time implementation of Computer Mouse using Hand Gesture Recognition. IM uses gesture rules corresponding to each mouse function and accepts video containing hand gestures as input. Gestures are extracted from video, matched with existing gesture rule set and appropriate mouse functionality is invoked. It plays an important role in Virtual Reality Environments as well as areas of Human-Computer Interfacing. In this work, we propose a vision based, single camera model that uses 2D-tree based virtual grid for camera-to-screen coordinate mapping. The proposed model is cost effective, easy to set up and provides same functionality of hardware mouse. It overcomes the inadequacy of earlier approaches. The proposed method provides satisfactory results for various texture backgrounds under uniform illumination. © 2012 by IJTS.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2020

A. Krishna Gs, Pon, V. Nirmal, Rai, S., and A. Baskar, “Vision System with 3D Audio Feedback to assist Navigation for Visually Impaired”, Procedia Computer Science , vol. 167(2):235-243. International Conference on Computational Intelligence and Data Science, 2020.[Abstract]


Freedom of movement, identification of humans and material objects, and interaction with the environment still pose a challenge in the development of assistive devices for the visually impaired. The design of assistive devices is generally accomplished by integration of sensors, vision systems, tactile, and audio feedback systems. This paper proposes a vision system with a 3D audio feedback mechanism, for reliable navigation by the visually impaired. The variations in sound intensity of earphones facilitate a natural and intuitive cognizance of the relative positions of objects, in a pathway. The proposed system is comprised of three main modules: depth calculation, where a depth map is found using stereoscopic vision; object detection, where a trained Convolutional Neural Network (CNN) is used to identify doors, and extract their location; and, 3D audio generation, which generates an audio vector, from the depth map and an object’s location. The audio vector is then used to generate a spatial audio signal for the user. This system proved to be useful and accurate for navigation by the visually impaired, when tested in a real-life environment.

More »»

2008

R. Naga Yathindra Gupta, E. Rao, U., A. Baskar, and R. Karthi, “Two-step iterative algorithm to extract generative video parameters from video sequences”, Proceedings - International Conference on Computational Intelligence and Multimedia Applications, ICCIMA 2007, vol. 3. Sivakasi, Tamil Nadu, pp. 458-463, 2008.[Abstract]


GV (Generative Video) is a framework for the analysis and synthesis of video sequences. In GV, the operational units are not the actual frames in the original sequence; it has world images which have the non redundant information about the video sequences and the ancillary data. The world images and the ancillary data form the generative video representation, the information that is needed to regenerate the original video sequence. A two-step iterative algorithm is used here to obtain the generative video parameters. The first step estimates the background texture for a fixed template. The second step estimates the object template for a fixed background-the solution is given by a simple binary test evaluated at each pixel. The algorithm converges in a few iterations, typically three to five iterations. © 2007 IEEE.

More »»

Publication Type: Conference Paper

Year of Publication Title

2018

A. Baskar and Dr. Gireesh K. T., “Facial Expression Classification Using Machine Learning Approach: A Review”, in Advances in Intelligent Systems and Computing, 2018, vol. 542, pp. 337-345.[Abstract]


Automatic Facial Expression analysis has enthralled increasing attention in the research community in excess of two decades and its expedient in many application like, face animation, customer satisfaction studies, human-computer interaction and video conferencing. The precisely classifying different emotion is an essential problem in facial expression recognition research. There are several machine learning algorithms applied to facial expression recognition expedition. In this paper, we surveyed three different machine learning algorithms such as Bayesian Network, Hidden Markov Model and Support Vector machine and we attempt to answer following questions: How classification algorithm used its characteristics for emotion recognition? How various parameters in learning algorithm is devoted for better classification? What are the robust features used for training? Finally, we examined how advances in machine learning technique used for facial expression recognition?. © Springer Nature Singapore Pte Ltd. 2018.

More »»

2015

M. P. Nevetha and A. Baskar, “Applications of Text Detection and its Challenges: A Review”, in ACM International Conference Proceeding Series, ACM New York, NY, USA ©2015 , 2015, pp. 712-721.[Abstract]


The rising need for automation of systems has effected the development of text detection and recognition from images to a large extent. Text recognition has a wide range of applications, each with scenario dependent challenges and complications. How can these challenges be mitigated? What image processing techniques can be applied to make the text in the image machine readable? How can text be localized and separated from non textual information? How can the text image be converted to digital text format? This paper attempts to answer these questions in chosen scenarios. The types of document images that we have surveyed include general documents such as newspapers, books and magazines, forms, scientific documents, unconstrained documents such as maps, architectural and engineering drawings, and scene images with textual information.

More »»

2015

S. Gautam, Sivaraman, K. S., Muralidharan, H., and A. Baskar, “Vision System with Audio Feedback to Assist Visually Impaired to Grasp Objects”, in Procedia Computer Science, 2015, vol. 58, pp. 387–394.[Abstract]


In recent times, there have been many products that cater to the visually challenged, but only few have been readily available for regular use. The reason being, that the technology driving these products are costly, or complex to use. In this work, we propose a “Vision system with audio feedback to assist visually impaired to grasp objects”. Our proposed system eliminates these challenges, in its usability, complexity and functionality. The system is designed to serve the following: (1) Finding a desired object in the scene, in which, the object recognition is done using Weighted Matrix Algorithm from the visual input received from the camera; and (2) Assisting the user to the object's proximity, where, the user is guided using audio-feedback, at every step. This approach is represented taking the example of a commonly found object in our household. We have considered a water bottle. The above approach is found to produce suitable results.

More »»

2015

M. P. Nevetha and A. Baskar, “Automatic Book Spine Extraction and Recognition for Library Inventory Management”, in ACM International Conference Proceeding Series, New York, NY, USA, 2015, pp. 44-48.[Abstract]


Manual inventory management in a library is by far arduous. Automation of book inspection can be achieved by using a simple camera based system that can recognize book spines in a book shelf. The book spines contain printed information such as title, author and publisher name, which can be extracted and verified with the library's database. Book spines can be segmented by detecting their rectangular boundaries which appear as straight lines. Line detection using hough transform and line segment detector may result in spurious boundaries due to the presence of long titles or graphics on the book spine. In this paper, we propose a technique to improve book spine border detection by devising set of constraints based on structural properties that can be used to filter the detected line segments so as to obtain book spine boundaries. The segmented book spines are binarized to extract the printed information such as title, author and publisher name. The text is recognized using Tesseract Optical Character Recognition Engine. The proposed algorithm was tested successfully on book shelf images with vertically oriented, uniformly inclined and multi-oriented book spines.

More »»

2007

A. Baskar, PrabuKumar, M., and Sathishkumar, S., “Improved adaptive skip algorithm for video shot boundary detection”, in Proceedings of ICSCN 2007: International Conference on Signal Processing Communications and Networking, Chennai, 2007, pp. 492-496.[Abstract]


Video shot boundary (VSB) detection plays an important role in modern video archiving and summarization applications. The classical linear approach towards VSB detection is basically a sequential search, however this approach is computationally very expensive for large databases. In this work we propose a non-linear approach for VSB detection, which is an improvement of existing adaptive skip. The proposed technique compares less than 10% of frames in an entire video. Our experimental result shows that the proposed technique outperforms the other existing non-linear algorithms with better accuracy and meaningful VSBs. © 2007 IEEE.

More »»