Abstract：In this paper a fast algorithm is proposed to detect and classify human faces.Querying the color table,the system firstly selects out the face area from the image.During the pose elassification each eigenspace is compressed individually to reduce the computation of training and classification of faces.Experiments testify the good performance of detection and classification.
陈茂林, 戚飞虎. 人脸图像检测及分类系统的研究[J]. 电子学报, 2001, 29(S1): 1917-1919.
CHEN Mao-lin, QI Fei-hu. Research on the Human Face Detection and Its Classification. Chinese Journal of Electronics, 2001, 29(S1): 1917-1919.
[1] V Govindaraju.Locating human faces in photographs[J].lnt.J.Comp.Vision,1996,19(20):129-146.[2] J Cai,A Goshtasby.Detecting human faces in color images [J].Image and vision computing 1999,18:63-75.[3] Haiyuan Wu,Qian Chen and Massahiko Yachida.Face detection from color images using a fuzzy pattern method [J].IEEE Trans.,1999,PA-MI-21(6):557-563.[4] Toshiaki Kondo,Hong Yan.Automatic human face detection and recognition under non-uniform illumination [J].Pattern Recognition,1997,32:1707-1718.[5] Douglas Chai,King N.Ngan.Face segmentation using skin-color map in videophone applications [J].IEEE Trans.circuits and systems for video tech.,1999,9(4):551-564.[6] M A Turk,A P Pentland.Face recognition using eigenfaecs [A].In Proc.IEEE Conf.on Computer Vision and Pattern Recognition [C],Hawash,1991:586-591.[7] Liu Rujie,Yuan Baozong.Eigenspace-based human face detection[A].Proceedings of ICSP Beijing [C],2000:1305-1308.
2001, Vol. 29 
