Abstract
In recent years, video-based face recognition has been one of the hottest topics in the field of pattern recognition. How to fully utilize both spatial and temporal information in video to overcome the difficulties existing in the video-based face recognition, such as low resolution of face images in video, large variations of face scale, radical changes of illumination and pose as well as occasionally occlusion of different parts of faces, is the focus. In this paper, we propose a novel manifold-based semi-supervised face recognition algorithm using clustering (SS-CVLPP), which can discover more space-time semantic information hidden in video face sequence, simultaneously make full use of the small amount of labeled data with the plentiful unknown information and the intrinsic nonlinear structure information to extract discriminative manifold features. We also compare our approach with other algorithms on UCSD/Honda and our own video databases. The experimental results show that SS-CVLPP can get a higher recognition accuracy rate for video-based face recognition.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call