Subspace Face Recognition
主 题: Subspace Face Recognition
报告人: Xiaoou Tang (MSRA Manager)
时 间: 2006-05-11 下午 2:00 - 4:00
地 点: 理科一号楼 1560
Automatic face recognition has great potential in a large array of application areas, including security system access control, video surveillance, mug-shot matching for law enforcement, duplicate ID card detection, and multimedia information retrieval. In this talk, we focus on several recently developed algorithms in face recognition research. We first describe a framework that unifies current subspace face recognition algorithms. Under this framework, we can clearly see the advantage and disadvantage of each individual algorithm and discover the inherent relationship among different subspaces as well as their unique contributions to the extraction of discriminating information from the face images. We will also briefly discuss extension of the work based on random sampling and mixture models. At the end of the talk, we will show a few demos of other computer vision research topics from the visual computing group of MSRA.