DocumentCode :
383381
Title :
Robust face detection and hand posture recognition in color images for human-machine interaction
Author :
Terrillon, Jean-Christophe ; Pilpré, Arnaud ; Niwa, Yoshinori ; Yamamoto, Kazuhiko
Author_Institution :
Office of Regional Intensive Res. Project, Softopia Japan Found., Gifu, Japan
Volume :
1
fYear :
2002
fDate :
2002
Firstpage :
204
Abstract :
A system for the detection of human faces and for the classification of hand postures in color images is presented. We first propose to apply a combination of a skin chrominance-based image segmentation with a color vector gradient-based edge detection to efficiently detect faces and hands. A statistical model for face detection based on invariant moments is then used to discriminate between faces and hands in the segmented images. A novel approach to hand posture recognition based on phase-only correlation is finally applied to classify a subset of static hand postures of the Japanese sign language, each posture representing a given phoneme, and also to discriminate between hand postures and the image scene background. Experiments show that the additional use of the color gradient significantly improves the correct rate of face detection, and that the phase-only correlation filter yields a high rate of discrimination between different static hand postures as well as between hand postures and the scene background.
Keywords :
edge detection; face recognition; image classification; image segmentation; Japanese sign language; color images; color vector gradient-based edge detection; hand posture recognition; human-machine interaction; phase-only correlation filter; robust face detection; scene background; skin chrominance-based image segmentation; statistical model; Color; Face detection; Face recognition; Humans; Image edge detection; Image recognition; Image segmentation; Layout; Man machine systems; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
ISSN :
1051-4651
Print_ISBN :
0-7695-1695-X
Type :
conf
DOI :
10.1109/ICPR.2002.1044652
Filename :
1044652
Link To Document :
بازگشت