ECE: Electrical & Computer Engineering
ECE News


12:00 AM - 10:30 AM on Friday, September 13, 2013
Location: Virginia Tech Research Center - Arlington; Room 4-024; 900, N Gl

Invited Speaker: Dr. Harry Wechsler, George Mason University

The talk addresses the interplay between biometric challenges and solutions geared to develop and deploy robust face recognition applications that can operate under uncontrolled settings, adversarial encounters, and data (video) streaming conditions. Challenges addressed include uncontrolled A-PIE (Age / Plastic Surgery, Pose, Illumination, and Expression) settings, incomplete / masquerading information characteristic of denial and deception, outlier / imposter detection, varying data distributions, data fusion, and interoperability. The talk leverages image analysis / computer vision, machine and statistical {multi-task, ensemble, active} learning for face (object) recognition, re-identification, and surveillance / tracking applications. The solutions discussed are driven by regularization, similarity and rankings, and collective{multi-label and component-based} classification methods. The talk concludes with an all encompassing view on biometrics that covers appearance, behavior, and cognitive state for the intertwined purpose of authentication, data mining, and situation awareness.

Speaker's Bio:
Dr. Harry Wechsler serves as Professor of Computer Science at George Mason University. His research focus covers adversarial learning, biometrics, change and anomaly / outlier detection, cyber security, identity management, interoperability, performance evaluation, re-identification, and multi-task learning. He organized and directed the seminal NATO Advanced Study Institute (ASI) on “Face Recognition: From Theory to Applications” (Sterling, UK, 1997), directed the design and development of FERET facial database, and authored Reliable Face Recognition Methods (Springer, 2007). He is the author of 3 books and over 300 scientific papers. Dr. Wechsler holds (together with his doctoral students) 7 patents. He is an IEEE Fellow and an IAPR (Int. Assoc. for Pattern Recognition) Fellow.