Abstract: Face skin color detection is sensitive to illumination variations. This paper presented a novel method to detect the face skin color regions in complicated illumination conditions. Firstly, a skin color model in complicated illumination conditions was created using YCbCr color space. Secondly, the skin color model was applied to detect the face skin color regions in the input image. Finally, the 4-connected regions were calculated in the detection result and be used to eliminate the non-face regions and recover the real face regions. The experimental results demonstrate that the proposed method can detect the face skin color regions correctly in complicated illumination conditions.

Key words: YCbCr, skin color model, face skin color detection, different illumination conditions, 4-connected regions

摘要： 复杂光照对人脸肤色检测具有重要影响。在YCbCr颜色空间建立复杂光照条件下的人脸肤色模型,然后利用该模型检测人脸图像的肤色区域,并对检测结果利用4-连通区域的几何特征消除非人脸区域,最后利用连通元复原误检的人脸肤色区域。实验结果表明,该方法可以实现复杂光照下人脸肤色区域的准确检测。

关键词: YCbCr, 肤色模型, 人脸肤色检测, 光照多变, 4-连通元