Automatic extraction of human facial features

被引:10
作者
Mu, FH [1 ]
Li, HB [1 ]
Forchheimer, R [1 ]
机构
[1] LINKOPING UNIV,DEPT ELECT ENGN,IMAGE CODING GRP,S-58183 LINKOPING,SWEDEN
关键词
model-based image coding; computer vision; videophone communication; human facial feature extraction; face identification;
D O I
10.1016/0923-5965(95)00056-9
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
This paper addresses a method of extracting human facial features from the head-and-shoulder images used in videophone communications. A basic idea behind the scheme is to make full use of the information in both the temporal and spatial domains to detect facial features. The new approach to facial feature extraction consists of a temporal and a spatial eye-mouth finder (EMF). The temporal technique eliminates the influence of background and gives a rough and reliable position estimation of the interesting objects, e.g. eyes and mouth, and the latter reaches an accurate result which is needed in videophone communications. Another characteristic of this method is its simplicity. Some basic operators can be used twice, i.e., they are used not only in the temporal domain but also in the spatial domain. The results on the test image sequences are satisfactory.
引用
收藏
页码:309 / 326
页数:18
相关论文
共 14 条
[1]  
Aizawa K., 1989, Signal Processing: Image Communication, V1, P139, DOI 10.1016/0923-5965(89)90006-4
[2]  
[Anonymous], P INT PICT COD S
[3]  
[Anonymous], IMAGE COMMUN
[4]   THE LAPLACIAN PYRAMID AS A COMPACT IMAGE CODE [J].
BURT, PJ ;
ADELSON, EH .
IEEE TRANSACTIONS ON COMMUNICATIONS, 1983, 31 (04) :532-540
[5]  
Chellapa R., 1995, P IEEE, V83
[6]  
FORCHHEIMER R, 1989, IEEE T ACOUST SPEECH, V37
[7]  
Haralick R. M., 1992, COMPUTER ROBOT VISIO, V1
[8]  
HUANG M, 1993, OPT ENG, V32
[9]  
HUANG TS, 1991, P SOC PHOTO-OPT INS, V1605, P234, DOI 10.1117/12.50243
[10]  
LI H, 1993, THESIS LINKOPING U