DocumentCode :
1742887
Title :
Pre-attentive detection of perceptually important regions in facial images
Author :
Golovan, Alexander ; Myung-Hyun Yoo ; Lee, Seong-Whan
Author_Institution :
Korea Univ., Seoul, South Korea
Volume :
1
fYear :
2000
fDate :
2000
Firstpage :
1092
Abstract :
The cascade method, a way of calculating orientation components in an image, was developed to extract some important regions from a given image of a human face. By combining local orientation components and thresholding them, we construct five feature maps and a final composite map which is a linear combination of the five maps. As in human visual perception, the composite map operates like pre-attentive processing in the early stage of vision, and then shows robustness in selecting the most informative areas of images. For 50 non-normalized face images from the ORL database, it showed 91% detection accuracy which is the ratio of corresponding points between the feature maps of a whole image and the same maps of important regions in that image such as eyes, nose and mouth, etc
Keywords :
face recognition; feature extraction; image segmentation; cascade method; composite map; eyes; facial images; feature maps; local orientation components; mouth; nose; orientation components; perceptually important regions; pre-attentive detection; thresholding; Eyes; Face detection; Humans; Image databases; Mouth; Nose; Robustness; Spatial databases; Visual databases; Visual perception;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition, 2000. Proceedings. 15th International Conference on
Conference_Location :
Barcelona
ISSN :
1051-4651
Print_ISBN :
0-7695-0750-6
Type :
conf
DOI :
10.1109/ICPR.2000.905662
Filename :
905662
Link To Document :
بازگشت