一种综合颜色、纹理信息的皮肤检测方法

针对目前许多皮肤检测方法只考虑了像素级别上的颜色信息，未较好地利用图像空间上的其他信息，如纹理信息以及光照条件对成像颜色所造成的影响，在SPM方法的基础上提出了改进。首先引入“灰色世界”算法对因非标准光照所产生的颜色改变进行校正，有效提高了正检率。对SPM方法的输出部分通过灰度共生矩阵提取图像的纹理信息，过滤颜色信息为皮肤而纹理信息为非皮肤的像素区域，有效降低了误检率。实验结果表明，该方法取得了较好的效果。

A Method of Skin Detection Based on SPM Using Color and Texture Information

At present many skin detection methods only consider the pixel -level color information, and do not use other information of image in space, such as texture information and the impact of the lighting condi- tions. Based on SPM method, A new skin detection method using color and texture information is proposed. First, using GrayWorld algorithms are used to correct the color of image caused by non - standard illuminants to improve the performance of true detection. The texture information is extracted by using the co - occurrence matrix of gray image to filter pixels that the colors are skin - like. Experimental results shows that this method is performanced better than the SPM method.