基于Adaboost与肤色分割融合的驾驶员图像脸部检测

摘要

An improved face detection algorithm based on Adaboost is used to detect the face area possibly existing in the image, the detected area is extended properly and an face detection algorithm based on skin color segmentation in RGB space is used to locate the face again in the extended area, accurate fusion detection algorithm of face is achieved by the defined area coincidence degree and the geometric features of human face. Experiment results show the robustness and real-time performance of the algorithm.%采用改进的基于Adaboost的人脸检测算法检测出可能存在的初始人脸区域,适当扩大初始人脸区域的面积,在此基础上,利用基于RGB颜色空间的肤色分割算法进行人脸区域的二次定位,根据定义的脸部区域重合度和人脸几何特征实现对脸部区域的精确融合检测.实验结果证实了该算法的鲁棒性和实时性.