基于肤色和Adaboost算法的人脸检测  

Face Detection Based on Skin Color and Adaboost Arithmetic

作　　者：付炜[1] 孔祥栋[1] 

机构地区：[1]燕山大学信息学院,河北秦皇岛066004

出　　处：《现代电子技术》2010年第6期131-134,共4页Modern Electronics Technique

摘　　要：人脸检测是人脸识别的第一环节,也是非常关键的环节。试验中主要针对静态彩色图像进行人脸检测,研究肤色在人脸检测中的应用。不同图像背景、人脸的可变性和光照条件变化都增加了人脸检测的难度。因此,从一幅图像中检测人脸是一项具有挑战性的任务。采用Adaboost的人脸检测,并提出肤色与Adaboost算法相结合的人脸检测方法。对输入的彩色图像进行从RGB空间到YCbCr空间的转换,然后进行肤色分割,排除背景干扰,最后用Adaboost算法对可能区域进行检测,得到人脸位置。实验表明,该方法误检率低,鲁棒性好,对人脸检测有较强的实用性。Face detection is the first link and a key link in face recognition, static color image is used for detecting human face, and the primary research is skin color application in face detection. Different image background, face variability and change in light conditions have increased the difficulty of face detection. Therefore, face detection from an image is a challenge. Adaboost algorithm is used to detect human face,and a new method of face detection,which combines skin color with Adaboost is presented. Conversion of the input image from RGB to RCbCr,and then skin color is segmented, background interference is ex- cluded,Adaboost is used to get face location from possible regional. Experiments show that this method has low rate of false detection,good robustness,and strong practicality to face detection problem.

关 键 词：人脸检测 ADABOOST算法 HAAR特征 肤色分割 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]