Academic Journal
Using statistical characteristics of gradient phases for robust face recognition under illumination variations.
| Title: | Using statistical characteristics of gradient phases for robust face recognition under illumination variations. |
|---|---|
| Authors: | Ching-Yao Su, Jar-Ferr Yang |
| Source: | IET Computer Vision (Wiley-Blackwell); 2015, Vol. 9 Issue 3, p408-418, 11p |
| Abstract: | Gradient phase, which is treated as an illumination insensitive measure, is an important feature for visual detection and recognition applications, especially under illumination variations. However, fewer statistical characteristics of the gradient phase have been reported till now. First, the statistical characteristics of the gradient phase against gradient signal-to-noise ratios (gradient SNRs) were investigated. The analysed results show that the confidence (or standard deviation) of gradient phases against gradient SNRs should never be linearly related, as is usually supposed. With the help of the statistical analyses of the gradient phase, the gradient-based visual detection and recognition were improved by incorporating confidence information into the cost function. Moreover, inspired by the analysed characteristics of the gradient phase, an enhanced gradientface method is proposed to improve the performance of the gradient phase-based face recognition. Intensive simulations and comparisons are performed to show its superior performance without the side effect of discrimination loss that existed in some illumination normalisation approaches. [ABSTRACT FROM AUTHOR] |
| Subject Terms: | HUMAN facial recognition software, ROBUST control, APPLICATION software, SIGNAL-to-noise ratio, INFORMATION theory |
| Copyright of IET Computer Vision (Wiley-Blackwell) is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| ISSN: | 17519632 |
| DOI: | 10.1049/iet-cvi.2013.0168 |
| Database: | Complementary Index |
Availability