Dr. Ioannis A. Kakadiaris
Depts. of Computer Science, Electrical & Computer Engineering, Biomedical Engr.
University of Houston, TX
Time: October 10th 2014, 11:00am
Location: EB 3105
Abstract:Research in the Computational Biomedicine Laboratory (www.cbl.uh.edu) is motivated by fundamental open problems in computer vision, image analysis, machine learning, and pattern recognition with an emphasis on applications that address some of society's greatest challenges. The lab fosters innovative collaborations with other institutions, creates transferable technology, and disseminates results to scientific and medical communities and the general public. The Biometrics cluster of CBL examines research problems in the areas of face recognition and facial expression analysis. Our have made contributions in the areas of 3D face (and ear) recognition, 3D-aided 2D Face Recognition, 2D-2D Face Recognition, and profile-based face recognition. Our 3D-3D face recognition software ranked first in the 3D-shape section of the 2007 Face Recognition Vendor Test (FRVT) organized by NIST, while our 3D-2D method outperforms the state of the art 2D face recognition methods. Currently, we are working in addressing critical challenges including low resolution data, indoor/outdoor illumination, accurate landmark and pose estimation, cross-resolution matching, and score normalization. In the area of machine learning we are working towards developing novel methods for: (i) data representations by learning the basis, the representation and the metric simultaneously, (ii) classifying imbalanced datasets, and (ii) sparse representations for missing and incomplete data. The Biomedical Computing Cluster examines research problems arising in cardiovascular informatics, cancer informatics and neuro-informatics. In cardiovascular informatics, we seek to develop a new scoring paradigm that will capture the individuals that are risk of having a heart attack in the next 12 months. Finally, understanding how neurons work requires fundamental understanding of their structure. The presentation will highlight exciting research challenges and outstanding research topics.
Bio:Ioannis A. Kakadiaris is a Hugh Roy and Lillie Cranz Cullen University Professor of Computer Science, Electrical & Computer Engineering, and Biomedical Engineering at the University of Houston (UH). He joined UH in August 1997 after a postdoctoral fellowship at the University of Pennsylvania. Ioannis earned his B.Sc. in physics at the University of Athens in Greece, his M.Sc. in computer science from Northeastern University, and his Ph.D. at the University of Pennsylvania. He is the founder of the Computational Biomedicine Lab (www.cbl.uh.edu) and in 2008 he directed the Methodist-University of Houston-Weill Cornell Medical College Institute for Biomedical Imaging Sciences (IBIS) (ibis.uh.edu). His research interests include biomedical image computing, computer vision, pattern recognition with application on cardiovascular informatics, cancer informatics, neuro-informatics, face recognition, and energy informatics. Dr. Kakadiaris is the recipient of a number of awards, including the NSF Early Career Development Award, Schlumberger Technical Foundation Award, UH Computer Science Research Excellence Award, UH Enron Teaching Excellence Award, and the James Muller Vulnerable Plaque Young Investigator Prize. His research has been featured on The Discovery Channel, National Public Radio, KPRC NBC News, KTRH ABC News, and KHOU CBS News. Selected professional service leadership positions include: General Co-Chair of the 2013 Biometrics: Theory, Applications and Systems Conference (BTAS 2013), General Co-chair of the 2015 SPIE Biometric and Surveillance Technology for Human and Activity Identification, Program Co-Chair of the 2015 International Conference on Automatic Face and Gesture Recognition Conference, and Vice-President for Technical Activities for the IEEE Biometrics Council.
Dr. Arun Ross