26 May 2011 A new approach for skin recognition in near-infrared images
Author Affiliations +
In this paper, we proposed a new skin recognition approach for human identification. An automatic skin segmentation method is developed to detect the location of eyes and the skin area. A 1D Log-Gabor filter is used for skin feature extraction and template generation. And the center area of the skin template is matched with the database. The experimental results show that the proposed skin recognition method can achieve better performance compared to face recognition systems when it is used on the CASIA-Iris-Distance.
© (2011) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Zhi Zhou, Eliza Y. Du, Edward J. Delp, "A new approach for skin recognition in near-infrared images", Proc. SPIE 8063, Mobile Multimedia/Image Processing, Security, and Applications 2011, 80630J (26 May 2011); doi: 10.1117/12.884232; https://doi.org/10.1117/12.884232

Back to Top