25 March 2017 Local intensity area descriptor for facial recognition in ideal and noise conditions
Author Affiliations +
Abstract
We propose a local texture descriptor, local intensity area descriptor (LIAD), which is applied for human facial recognition in ideal and noisy conditions. Each facial image is divided into small regions from which LIAD histograms are extracted and concatenated into a single feature vector to represent the facial image. The recognition is performed using a nearest neighbor classifier with histogram intersection and chi-square statistics as dissimilarity measures. Experiments were conducted with LIAD using the ORL database of faces (Olivetti Research Laboratory, Cambridge), the Face94 face database, the Georgia Tech face database, and the FERET database. The results demonstrated the improvement in accuracy of our proposed descriptor compared to conventional descriptors [local binary pattern (LBP), uniform LBP, local ternary pattern, histogram of oriented gradients, and local directional pattern]. Moreover, the proposed descriptor was less sensitive to noise and had low histogram dimensionality. Thus, it is expected to be a powerful texture descriptor that can be used for various computer vision problems.
© 2017 SPIE and IS&T
Chi-Kien Tran, Chi-Kien Tran, Chin-Dar Tseng, Chin-Dar Tseng, Pei-Ju Chao, Pei-Ju Chao, Hui-Min Ting, Hui-Min Ting, Liyun Chang, Liyun Chang, Yu-Jie Huang, Yu-Jie Huang, Tsair-Fwu Lee, Tsair-Fwu Lee, } "Local intensity area descriptor for facial recognition in ideal and noise conditions," Journal of Electronic Imaging 26(2), 023011 (25 March 2017). https://doi.org/10.1117/1.JEI.26.2.023011 . Submission: Received: 8 November 2016; Accepted: 14 March 2017
Received: 8 November 2016; Accepted: 14 March 2017; Published: 25 March 2017
JOURNAL ARTICLE
10 PAGES


SHARE
RELATED CONTENT


Back to Top