Abstract:
In many computer vision problems, the main task is to match two images of an object (e.g., face, iris, vehicle, etc.) that may exhibit appearance differences due to factors such as translation, rotation, scale change, occlusion and illumination variation. One class of methods to achieve accurate object recognition in the presence of such appearance variations is one where features computed in a sliding window in the target image are compared to features computed in a stationary window of the reference image. Correlation filters are an efficient frequency-domain method to implement such sliding window matching. They also offer benefits such as shift-invariance (i.e., the object of interest doesn't have to be centered), no need for segmentation, graceful degradation and closed-form solutions. While the origins of correlation filters go back more than thirty years, there have been some interesting and useful recent advances in correlation filter designs and their applications. For example, the recently-introduced maximum margin correlation filters (MMCFs) show how the superior localization capabilities of correlation filters can be combined with the excellent generalization capabilities of support vector machines (SVMs). Another major research advance is the development of vector correlation filters that are designed to match vector features (e.g., HOG) extracted from the input image rather than just input image pixel values. While past application of correlation filters focused mainly on automatic target recognition, more recent applications include face recognition, iris recognition, palmprint recognition and visual tracking. This talk will provide an overview of correlation filter designs and applications, with particular emphasis on these more recent advances. If time permits, we will also briefly summarize our recent research in using crowd-sourced vehicle sensor signals to extract useful road information such as location of potholes.

Biography:
Prof. Vijayakumar ("Kumar") Bhagavatula received his Ph.D. in Electrical Engineering from Carnegie Mellon University (CMU), Pittsburgh and since 1982, he has been a faculty member in the Electrical and Computer Engineering (ECE) Department at CMU where he is now the U.A. & Helen Whitaker Professor of ECE and the Associate Dean for Graduate and Faculty Affairs in the College of Engineering. Professor Kumar's research interests include Pattern Recognition and Coding and Signal Processing for Data Storage Systems and for Digital Communications. He has authored or co-authored over 600 technical papers, twenty book chapters and one book entitled Correlation Pattern Recognition. He served as a Topical Editor for Applied Optics and as an Associate Editor of IEEE Trans. Information Forensics and Security. Professor Kumar is a Fellow of IEEE, SPIE, Optical Society of America (OSA) and the International Association of Pattern Recognition (IAPR).

Host:
Dr. Arun Ross