DocumentCode :
1739667
Title :
Face contour extraction with active shape models embedded knowledge
Author :
Yong, Li ; Changshui, Zhang ; Xiaoguang, Lv ; Zhang, David
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Volume :
2
fYear :
2000
fDate :
2000
Firstpage :
1347
Abstract :
Face contour is an important feature of the human face and can be used for face indexing and retrieval. The key idea of face contour extraction here is to use the knowledge of the human face. We integrate the knowledge of the human face into the original active shape models (ASM) search. Due to the disturbance of hair, ears, eyes, mouth, or other noise, the face contour can not be exactly obtained by the original ASM method, so specific knowledge of the human face is employed in our method for more accurate face contour extraction. Experiments show the effectiveness of the proposed approaches
Keywords :
edge detection; feature extraction; knowledge based systems; active shape models embedded knowledge; face contour extraction; face indexing; face retrieval; human face feature; Active shape model; Automation; Covariance matrix; Ear; Eyes; Face; Hair; Humans; Indexing; Mouth;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal Processing Proceedings, 2000. WCCC-ICSP 2000. 5th International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-5747-7
Type :
conf
DOI :
10.1109/ICOSP.2000.891795
Filename :
891795
Link To Document :
بازگشت