S
Stan Z. Li
Researcher at Westlake University
Publications - 625
Citations - 49737
Stan Z. Li is an academic researcher from Westlake University. The author has contributed to research in topics: Facial recognition system & Computer science. The author has an hindex of 97, co-authored 532 publications receiving 41793 citations. Previous affiliations of Stan Z. Li include Microsoft & Macau University of Science and Technology.
Papers
More filters
Book ChapterDOI
Face Anti-spoofing: Multi-spectral Approach
TL;DR: This chapter presents a multi-spectral face recognition system working in VIS (Visible) and NIR (Near Infrared) spectrums, which is robust to various spoofing attacks and user cooperation free, and has two advantages: its recognition rate is higher than the VIS subsystem and users' cooperation is no longer needed.
Proceedings ArticleDOI
Nearest manifold approach for face recognition
TL;DR: A manifold learning algorithm (MLA) for learning a mapping from highly-dimensional manifold into the intrinsic low-dimensional linear manifold and the nearest manifold (NM) criterion for the classification are presented and an algorithm for computing the distance from the sample to be classified to the nearest face manifolds in light of local linearity of manifold is presented.
Proceedings ArticleDOI
Real-time and accurate segmentation of moving objects in dynamic scene
TL;DR: A fast and efficient algorithm is presented for background update to handle various sources of scene changes, including ghosts, left objects, camera shaking, and abrupt illumination changes, and a novel filtering method is presented based on multiple scale and fast connected blob extraction.
Journal ArticleDOI
Enhanced Local Gradient Order Features and Discriminant Analysis for Face Recognition
TL;DR: Local order constrained IGOs are exploited to generate robust features and enhance the local textures and the order-based coding ability, thus discover intrinsic structure of facial images further.
Book ChapterDOI
Dynamic Texture Based Gait Recognition
TL;DR: A novel approach for human gait recognition that inherently combines appearance and motion is presented and a new coding of multiresolution uniform Local Binary Patterns is proposed and used in the construction of spatiotemporal LBP histograms.