基于肤色模型和FCM动态聚类的人脸检测

针对复杂背景下彩色图像中的人脸检测，研究一种基于非线性分段色彩变换、肤色模型和FCM动态聚类算法的检测方法．算法首先进行颜色空间映射及非线性分段色彩变换，再利用肤色分布模型，对肤色似然度图像进行自适应的肤色分割，进一步采用线段编码从分割后的图像中提取区域特征向量，最后利用FCM动态聚类方法，从复杂背景中检测出人脸区域．实验证明，该方法具有较高的准确性和适应性．

Face Detection Based on Skin Color Model and FCM Dynamic Clustering

A face detection method based on skin color space mapping,a nonlinear color transformation and FCM dynamic clustering algorithm for color images in complex background is presented.First,the color space is mapped and then nonlinear color transformation is made.After that,skin model is used for segmenting regions in which may have faces.Then,line code is used for drawing the eigenvector of area from the images which are segmented.At last,FCM dynamic clustering method is used for detecting the areas of human faces from complex background The experimental result of segmentation by means of the new algorithm is satisfactory.