中文摘要：

针对传统高斯肤色模型在肤色和光照变化较大情况下不能有效提取肤色区域的问题,提出一种改进的高斯肤色模型,并将其应用于人脸检测中。模型参数采用一种自适应更新的参数选择方法,通过对相似度人脸和灰度人脸在对应像素点加权相乘的方式,得到将肤色相似度信息和灰度分布信息有效结合的人脸肤色模型,并结合Adaboost算法设计了人脸检测方法。在FERET（facial recognition technology database）、LFW（labeled faces in the wild）、GTFD（Georgia Tech face database）和多人脸图库上的实验结果表明,该模型的肤色提取正确率比传统高斯肤色模型提高了27.1%,提出的人脸检测方法的检测率比Adaboost算法提高了5.5%。

英文摘要：

To solve the problem that traditional Gaussian skin color model is not very robust in skin segmentation under different skin colors and different illuminations,an improved Gaussian skin color model is proposed.The parameters of this proposed model can adapt to different faces.And this model combines Gaussian skin color model and gray level distribution through weighting multiplication.Then,a new face detection method based on the skin color model and Adaboost algorithm is proposed to detect faces.Experiments on FERET（facial recognition technology database）,LFW（labeled faces in the wild）,GTFD（Georgia Tech face database） and dataset of scene images including many faces demonstrate that the face skin color extraction rate of this proposed model is enhanced by 27.1% compared with the performance of traditional Gaussian model and enhanced by 5.5% compared with the performance of Adaboost algorithm.