Title :
Eigen features technique and its application
Author :
Hongxun, Yao ; Wen, Gao ; Mingbao, Liu ; Lizhuang, Zhao
Author_Institution :
Dept. of Comput. Sci. & Eng., Harbin Inst. of Technol., China
Abstract :
We introduce a basic technique, eigen features, which has been proved effectively in the field of human face perception. Its spirit is to represent pattern categories with essence of the data by getting rid of relativity among the data. We first describe the principle of eigen features and the measure of realization. Then, we introduce our three human face perception system which are based on eigen features-human face detection and tracking system, ID card photograph identification system and facial expression recognition system
Keywords :
eigenvalues and eigenfunctions; face recognition; feature extraction; image representation; tracking; ID card photograph identification system; eigen features; facial expression recognition system; human face detection; human face perception; human face perception system; human face recognition; human face tracking; pattern representation; Application software; Computer science; Computer vision; Deductive databases; Face detection; Face recognition; Humans; Natural languages; Speech recognition; Vectors;
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
DOI :
10.1109/ICOSP.2000.891747
