The primary focus of the talk will be on the characterization of facial deformation through strain patterns computed from the motion observed in facial expression videos and its application in image analysis tasks such as person identification and expression segmentation. The speaker will describe novel image analysis algorithms to follow facial strain patterns observed through video recording of faces in expressions. Specifically, we propose to use the strain pattern extracted from non-rigid facial motion as a simplified and adequate way to characterize the underlying material properties of facial soft tissues. Experimental results using the computational strategy developed through this work emphasize the uniqueness and stability of strain maps across adverse data conditions (low and shadow lighting and face camouflage) making it a promising feature for image analysis tasks that can benefit from such auxiliary information about the human face. With an increasing attention to multimodal techniques and the availability of effective fusion methods in image analysis systems deployed in many application domains, strain map adds an important dimension in our abilities to characterize a face.
Dmitry B. Goldgof has received Ph.D. degree from the University of Illinois. He is currently a Professor and Associate Chair of the Department of Computer Science and Engineering at the University of South Florida. Professor Goldgof research interests include Image and Video Analysis, Pattern Recognition and Bioengineering. Previously, Dr. Goldgof held visiting positions at the H. Lee Moffitt Cancer Center and Research Institute, Department of Computer Science at the University of California at Santa Barbara and Department of Computer Science at University of Bern in Switzerland. Dr. Goldgof has graduated 14 Ph.D. and 37 MS students, published over 65 journal and 145 conference papers, 16 books chapters and edited 4 books. Professor Goldgof is a Fellow of IEEE and is an Associate Editor for IEEE Transactions on Systems, Man and Cybernetics and for International Journal of Pattern Recognition and Artificial Intelligence.