一种基于肤色和脸部特征的人脸特征点检测算法

人脸检测通常是人机系统中人机交互的第一步,像人机系统中基于人体特征的用户身份识别,计算机对用户感情和意图的理解等.本文提出了一种用于办公室环境下的彩色图像中人脸检测算法.基于一种新的肤色检测算法,对图像进行肤色区域检测.算法通过构建眼,嘴模板来进行人脸的校验.实验结果表明,该算法可以实现在图像中出现照明,人脸表情,尺度较大范围变化情况下的人脸检测.

A Facial Feature Points Extraction Approach Based on Skin Color Regions and Facial Features

Human face detection is often the first step in HCI such as biometrics identification,perceiving the emotion and intention of users.A facial feature extraction algorithm is presented in this paper for color images in the presence of complex background.Based on a novel lighting compensation technique,skin regions can be detected over the entire image;the algorithm constructs eye and mouth maps for verifying each facial feature candidate.Experimental results demonstrate successful face detection over a wide variety of illumination,position,scale,orientation and expression in images for AR face database and other photo collections.