DocumentCode :
2641838
Title :
Eyes-strip extraction for detection of a human face
Author :
Tolba, A.S. ; Ashraf, M. ; Abu-Rezq, A.N.
Author_Institution :
Dept. of Phys., Kuwait Univ., Safat, Kuwait
fYear :
1999
fDate :
22-24 Nov. 1999
Firstpage :
109
Lastpage :
112
Abstract :
Face detection in a natural scene is an essential step in automated human face recognition. The eyes-strip of a human face plays the most important part in the detection process, since this area is not affected by hairstyle. Geometric techniques for feature extraction have the problems of sensitivity to lighting conditions and facial expressions. The weakness of the geometric techniques could be easily avoided using neural networks. In this paper, a learning vector quantization (LVQ) neural network is trained to detect the eyes-strip in skin-like areas only. First, a modified color system is used to extract skin-like areas from a natural scene. The fuzzy C-means algorithm is then used for thresholding the hue weighted chroma image. The skin-like area builds the basis of further search for human facial features. A LVQ network is trained on different eyes-strips and other areas of both facial and nonfacial images.
Keywords :
face recognition; feature extraction; image colour analysis; learning (artificial intelligence); neural nets; sensitivity; vector quantisation; LVQ network; automated human face recognition; detection process; eyes-strip; eyes-strip extraction; facial expression sensitivity; facial images; feature extraction; fuzzy C-means algorithm; geometric techniques; hairstyle; hue weighted chroma image thresholding; human face; human face detection; human facial features; learning vector quantization neural network; lighting condition sensitivity; modified color system; natural scene; neural network training; neural networks; nonfacial images; skin-like area extraction; skin-like areas; Face detection; Face recognition; Feature extraction; Humans; Layout; Neural networks; Physics; Skin; Strips; Vector quantization;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Microelectronics, 1999. ICM '99. The Eleventh International Conference on
Print_ISBN :
0-7803-6643-3
Type :
conf
DOI :
10.1109/ICM.2000.884817
Filename :
884817
Link To Document :
بازگشت