基于肤色模型的人脸检测研究

Research of Face Detection Based on Skin Colour Model

现有的人脸检测方法,对复杂光照环境下获得的彩色人脸图像的检测效果仍不太理想。在仔细研究目前人脸检测方法的基础上,对基于肤色分割结合模板匹配的人脸检测方法进行改进,提出基于"光照预处理+肤色模型+模板匹配"的人脸检测问题解决思路。实验结果表明,该方法对实际场景中正面和准正面的人脸图像,平均准检率达到84%,同时对光照变化不敏感,而且对姿态和表情的变化也具有较好的鲁棒性。

For the existing face detection methods can not achieve an ideal detecting effect for the colorized face image obtained in complex illumination environment, the face detection method based on skin color segmentation and template matching is improved, and a human faces detection method based on lighting pre-processing, skin model and template matching is pro- posed after making a study of the current face detection methods. Experimental results obtained with the new method show that the correct rate of detecting the positive and quasi-positive facial images in real environment is 84%, algorithm is insensitive for the illumination and has high robustness to the Changes in posture and expression of face images.