Professor Vijay Natarajan

Title: Symmetry in Scientific Data : An Approach to Feature-Directed Visualization

Abstract: Several natural and man-made objects exhibit symmetry in different forms, both in their geometry and in the material distribution. The study of symmetry plays an important role in understanding both the structure of these objects and their physical properties. In this talk, I will introduce the problem of symmetry detection in a scalar field, a real-valued function defined on a spatial domain of interest. The goal is to identify regions of interest within the domain of a scalar field that remain invariant under transformations of both domain geometry and the scalar values. Symmetry detection in scientific data is still a nascent area of research and existing methods that detect symmetry are either not robust in the presence of noise or are computationally costly.

I will present recently developed methods that detect symmetry in, potentially noisy, 3D scalar fields. The key ingredient of each algorithm is a data structure that captures topological and geometric properties of the scalar field. Finally, I will present applications including symmetry-aware volume visualization, volume editing, linked selection, and discuss how symmetry detection enables feature-driven and query-based exploration of scientific data.

Biography: Vijay Natarajan is an associate professor in the Department of Computer Science and Automation and the Supercomputer Education and Research Centre at the Indian Institute of Science, Bangalore. He received the Ph.D. degree in computer science from Duke University and holds a bachelors and masters degree in computer science and mathematics from BITS Pilani. His research interests include scientific visualization, computational geometry, and computational topology.

Professor Subhasis Chaudhuri

Title: Salient object detection and image co-segmentation

Abstract: Image saliency is a measure of "distinctiveness" of an object or a region in an image with respect to the background surrounding the object. Typically, these are the objects that capture our attention while viewing an image. The first part of the talk will deal with novel ways of extracting salient objects in a scene that try to do away with heuristics as much as possible. First, we discuss an algorithm that tries to retain the exact boundary of the detected salient objects. However, if one is interested in detecting only the bounding box of the salient object (say, for example in RoI-based image compression), we demonstrate how this can be done very efficiently using the seam carving technique.

If one is given, instead, a number of images sourced from various places and under different contexts, but having at least "something" in common, then the object common in all these images may be considered as the salient object. Extraction of this object in all these images is known as co-segmentation. In the second part of the talk, we shall discuss how this can be achieved using an approximate maximum common subgraph matching algorithm.

Biography: Subhasis Chaudhuri received his B.Tech. degree in Electronics and Electrical Communication Engineering from the Indian Institute of Technology, Kharagpur in 1985. He received the M.Sc. and the Ph.D. degrees, both in Electrical Engineering, respectively, from the University of Calgary, Canada and the University of California, San Diego. He joined the electrical engineering department at IIT, Bombay in 1990 as an assistant professor and is currently serving as the professor, Dean of International Relations and Deputy Director of IIT Mumbai. He served as the head of the department during the period 2005-2008. He has also served as a visiting professor at the University of Erlangen-Nuremberg, the Technical University of Munich and the University of Paris XI. He is a fellow of the Alexander von Humboldt Foundation, Germany, the Indian National Academy of Engineering, the Indian Academy of Sciences and the National Academy of Sciences. He is the recipient of Dr. Vikram Sarabhai Research Award for the year 2001, the Swarnajayanti Fellowship in 2003, and the S.S. Bhatnagar Prize in engineering sciences for the year 2004. He was awarded the J.C. Bose National Fellowship in 2008. He is a co-author of the books 'depth from defocus: a real aperture imaging approach', 'motion-free super-resolution', and 'ambulation analysis in wearable ECG', all published by Springer, NY. He has also edited a book on 'super-resolution imaging' published by Kluwer Academic in 2001. He is currently an associate editor for the journals IEEE Transactions in Pattern Analysis and Machine Intelligence, and International Journal of Computer Vision. He has served as the program chair for International Conference on Computer Vision (ICCV) held in Beijing in 2005. His research interests include pattern recognition, image processing, and computer vision.

Professor Venu Govinddaraju

Title: All Things Handwritten - OCR and Beyond

Abstract: Handwriting is gaining popularity with the advent of mobile devices which are now universally offering the provision for notes-taking and finger-writing. While the field of Optical Character Recognition (OCR) has matured when dealing with conversion of scanned printed document page images to editable text, it is faced with new challenges when dealing with handwritten matter especially when it is captured in the real-world by mobile devices.

Our foray into OCR technology begins with our success in reading postal addresses which has now extended to medical forms, prescriptions, scratch notes, and annotations. In this talk we will present some of the innovative techniques developed by our group, and describe several applications in the fields of transcription, search, security, and health, where further handwriting recognition advances can make a significant difference. 

Biography: Dr. Venu Govindaraju is a Distinguished Professor of Computer Science and Engineering at the State University of New York. He has authored over 400 scientific papers and supervised the doctoral dissertation of 33 students. His seminal work in handwriting recognition was at the core of the first handwritten address interpretation system used by the US Postal Service. He is a recipient of the 2010 IEEE Technical Achievement Award, the 2014 IIT Kharagpur Distinguished Alumnus Award and the 2015 IAPR Outstanding Achievement Award. He is a Fellow of the AAAS, ACM, IAPR, IEEE, and the SPIE.