基于AdaBoost算法的彩色图像人脸检测研究  

Color Image Face Detection Based on AdaBoost Algorithm

作　　者：孙士明[1] 王爱国[1] 纪友芳[1] 

机构地区：[1]中国石油大学计算机与通信工程学院,东营257061

出　　处：《微计算机应用》2011年第3期7-11,共5页Microcomputer Applications

摘　　要：在彩色图像中,不同的颜色所对应的灰度值可能相同,因此在灰度图像中检测不到的信息可能在彩色图像中被检测到。本文提出一种彩色积分图概念,在AdaBoost算法的分类器训练过程中分别得到彩色图像的人脸信息,并在分类器的后五层使用融合彩色信息的分类器分类。实验表明,本文方法增强了分类器的分类能力,提高了系统的正确检测率,降低了错误报警率。In color images, different colors may correspond to the same gray value, so there are some information that may not be detected in gray image but in color image. This paper presents a new image representation called the ＂Color Integral Image＂. In the improve AdaBoost algorithm, the color information were obtained from the color images and five in the post - classifiers use the classifiers that integrated of color information to classify the color images. The experimental results show that the method improved the performance of classifiers, accurate detection rates and decrease the classifiers＇ false alarm rates.

关 键 词：ADABOOST算法 人脸检测 积分图 彩色图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]