Share Email Print

Proceedings Paper

Upgrading the precision of face recognition using the gradient of a facet function
Author(s): Hee-Sung Kim; Jun Hee Cho
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

One of the major characteristics of human face is shown in the spatial curvature properties of face surface. The spatial curvature in object images can be represented by a set of gradient directions of the sub surfaces of the images. The image is appropriately divided into the same size of patches. Each patch is the sub surface of the image. A facet function on a patch can be obtained using the gray values of the pixels in the patch. A set of gradient directions of a group of the facet functions reflects one of the inherent curvatures of a face image. Two coefficients of the facet function indicate the gradient at the center of the patch. These coefficients form feature vectors for face discrimination or recognition. Computer computation suggests that the patch size of 5x5 yields the most precise recognition rate of 96.5.

Paper Details

Date Published: 20 February 2006
PDF: 10 pages
Proc. SPIE 6041, ICMIT 2005: Information Systems and Signal Processing, 60412X (20 February 2006); doi: 10.1117/12.664486
Show Author Affiliations
Hee-Sung Kim, The Univ. of Seoul (South Korea)
Jun Hee Cho, The Univ. of Seoul (South Korea)

Published in SPIE Proceedings Vol. 6041:
ICMIT 2005: Information Systems and Signal Processing
Yunlong Wei; Kil To Chong; Takayuki Takahashi, Editor(s)

© SPIE. Terms of Use
Back to Top