Perception-based Biometric Recognition: Challenges Demanding Unconventional Solutions
Recently biometric recognition, such as face verification (1:1 matching), face identification (1:N matching), or person re-identification, have been integrated into consumer devices, commercial security systems, law enforcement investigative tools, and defense/intelligence community surveillance platforms. However, there are challenges beyond conventional pose, illumination, and expression (PIE) conditions in need of multi-disciplinary solutions. Three such fundamental challenges (or concepts) that will be discussed include (1) cross-spectrum matching, (2) low-to-high resolution matching, and (3) bias estimation. A few recent advancements in the context of face and whole-body biometrics will be presented to attempt to illustrate that these problems demand “unconventional” solutions—solutions beyond leveraging more data, more nonlinearity, or more augmentation/diversity.
University of Nebraska, Lincoln on October 8, 2021 at 10:15 AM in EB3 2332
Dr. Benjamin S. Riggan is an assistant professor with the department of Electrical and Computer Engineering at the University of Nebraska-Lincoln (UNL), where he has worked since Fall of 2019. Prior to joining the faculty at UNL, he was a research scientist at the U.S. Army Research Laboratory (ARL) in the Networked Sensing and Fusion branch. His research interests are in the areas of computer vision, image and signal processing, and biometrics/forensics, especially related to domain adaptation, multi-modal analytics, and machine learning. Dr. Riggan received the B.S. degree in computer engineering from N.C. State University in 2009, and M.S. and Ph.D. degrees in electrical engineering from N.C. State University in 2011 and 2014, respectively. After finishing his Ph.D., he was awarded a postdoctoral fellowship at ARL’s Image Processing Branch. He has three best papers awards (IEEE WACV 2016, BTAS 2016, WACV 2018) and serves as Associate Editor for IEEE TAES.
This lecture series features exciting and dynamic visiting and virtual speakers from across the range of ECE disciplines. Take some time every Friday morning to be inspired by these great scientists and engineers before heading into the weekend!