Translator Disclaimer
Paper
15 November 2007 Adaptive skin detection based on online training
Author Affiliations +
Proceedings Volume 6788, MIPPR 2007: Pattern Recognition and Computer Vision; 678826 (2007) https://doi.org/10.1117/12.750929
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China
Abstract
Skin is a widely used cue for porn image classification. Most conventional methods are off-line training schemes. They usually use a fixed boundary to segment skin regions in the images and are effective only in restricted conditions: e.g. good lightness and unique human race. This paper presents an adaptive online training scheme for skin detection which can handle these tough cases. In our approach, skin detection is considered as a classification problem on Gaussian mixture model. For each image, human face is detected and the face color is used to establish a primary estimation of skin color distribution. Then an adaptive online training algorithm is used to find the real boundary between skin color and background color in current image. Experimental results on 450 images showed that the proposed method is more robust in general situations than the conventional ones.
© (2007) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ming Zhang, Liang Tang, Jie Zhou, and Gang Rong "Adaptive skin detection based on online training", Proc. SPIE 6788, MIPPR 2007: Pattern Recognition and Computer Vision, 678826 (15 November 2007); https://doi.org/10.1117/12.750929
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
Back to Top