2009年9月20日（星期日）10:30-11:30，蒙民伟楼404会议室
Face biometrics: Are there any limits to performance?
Josef Kittler
Distinguished Professor，英国皇家工程院院士，IEEE Fellow，IAPR Fellow
Centre for Vision, Speech and Signal Processing，University of Surrey, UK
Abstract :
The main factors considered to be challenging for the face biometric technology are illumination variation, pose, and the paucity of training data. Considerable advances have been made to confront these problems over the last five years, resulting in significant performance improvements that make face biometrics an attractive proposition for many applications. Measures developed to tackle these problems will be discussed, with a focus on illumination and pose, and their beneficial effect demonstrated.
Bio:
Josef Kittler is a Distinguished Professor of Machine Intelligence and Director of the Centre for Vision, Speech and Signal Processing at the University of Surrey. He holds a BA degree in Electrical Engineering, a Ph.D. in Pattern Recognition and a ScD, all from the University of Cambridge. He has worked on various theoretical aspects of Pattern Recognition, Image Analysis and Computer Vision, and on many applications including Image Coding, Image and Video Database Retrieval and Surveillance. His major contributions to pattern recognition include the k-nearest neighbour method, feature selection, and multiple expert fusion. In computer vision, contributions include robust statistical methods for shape analysis and detection, motion estimation and segmentation, and image segmentation by thresholding and edge detection. He has served as a member of the Editorial Board of IEEE Transactions on Pattern Analysis and Machine Intelligence and currently serves on the Editorial Boards of Image and Vision Computing, Pattern Recognition Letters, Pattern Recognition and Artificial Intelligence, Pattern Analysis and Applications.