提出一种肤色与Adaboost 方法相结合的人脸检测方法。首先把图像转换为YCbCr 颜色空间,然后利用肤色在CbCr 上的聚类性对图像进行预处理,最后,使用Adaboost 算法对候选人脸集进行细化,最终得到人脸集合。实验证明该方法的有效性。 关键词: 人脸检测肤色分割 Adaboost Abstract:A method of face detection combined skin color and Adaboost is proposed. The image is first transformed to YCbCr color space, and then use the feature of skin that gathering at the CbCr to dispose the image. Finally use the Adaboost method to refine the candidate face areas, and confirm the face areas at the end. The experiments demonstrate that the algorithm is effective. Key Words: face detection skin color segmentation Adaboost