Min Wu

University of Maryland, USA

Visual Processing and Data Science for Physiological Forensics


Many nearly invisible “micro-signals” have played important roles in media security and forensics, despite traditionally being regarded as interference or discarded as noise. These micro-signals are ubiquitous and typically an order of magnitude lower in strength or scale than the dominant ones. Physiological forensics is attracting attention in recent years, utilizing for example visual micro-signals that are the subtle changes in facial skin color following the pace of heartbeats. Video-based analysis of this repeating change provides a contact-free way to capture photo-plethysmogram (PPG), from which we can infer a person’s heart rate, breathing, blood oxygen level, and other physiological conditions. This talk will review the connections for micro-signal analysis between physiological forensics and other media forensic research, and highlight the synergistic roles of signal processing, computer vision, data science, security and privacy, and biomedical insights.

Speaker’s Bio

Min Wu is a Professor of Electrical and Computer Engineering and a Distinguished Scholar-Teacher at the University of Maryland, College Park, and Associate Dean of Engineering for Graduate Affairs. She received her undergraduate degrees from Tsinghua University, Beijing, China, in 1996 with the highest honors, and her Ph.D. degree in electrical engineering from Princeton University in 2001. At UMD, she leads the Media, Analytics, and Security Team (MAST), with main research interests on information security and forensics, multimedia signal processing, and applications of data science and machine learning for health and IoT. Dr. Wu was elected as IEEE Fellow, AAAS Fellow, and Fellow of the National Academy of Inventors. She was a founding member of APSIPA and elected to serve on its Board of Governors. She chaired the IEEE Technical Committee on Information Forensics and Security, and served as Editor-in-Chief of the IEEE Signal Processing Magazine. Currently, she is President-Elect (2022-2023) of the IEEE Signal Processing Society.