人眼定位与AdaBoost Gabor滤波的人脸检测算法

一般人脸检测率要受到光照的影响,而Gabor小波具有良好的生物视觉特性,对光照不敏感;在用AdaBoost算法训练分类器时,如果人脸在图像中位置相对固定,则分类器的分类能力会增强。为了解决光照问题对检测率的影响,提出人眼定位与AdaBoost Gabor滤波算法相结合的人脸检测方法。采用AdaBoost方法、Hough变换与直接最小二乘法拟合椭圆的方法确定眼睛的区域,并定位瞳孔与眼睑,根据五眼三庭知识得到人脸的区域,最后用AdaBoost Gabor滤波算法训练级联强分类器,并用此级联强分类器进行判别是否为人脸。在Yale、CMU Frontal Face等人脸库上进行实验,实验表明该方法不仅...

Full description

Saved in:
Bibliographic Details
Published in计算机应用研究 Vol. 31; no. 7; pp. 2201 - 2204
Main Author 杨定礼 张宇林 周红标 赵环宇 白秋产
Format Journal Article
LanguageChinese
Published 淮阴工学院电子与电气工程学院,江苏淮安,223003 2014
Subjects
AdaBoost
Gabor滤波
Hough变换
人眼定位
直接最小二乘法
人眼定位
eye location
AdaBoost Gabor滤波
AdaBoost Gabor filter
Hough transform
direct least squares method
直接最小二乘法
Hough变换
Online AccessGet full text
ISSN1001-3695
DOI10.3969/j.issn.1001-3695.2014.07.068

Cover

More Information
Summary:一般人脸检测率要受到光照的影响,而Gabor小波具有良好的生物视觉特性,对光照不敏感;在用AdaBoost算法训练分类器时,如果人脸在图像中位置相对固定,则分类器的分类能力会增强。为了解决光照问题对检测率的影响,提出人眼定位与AdaBoost Gabor滤波算法相结合的人脸检测方法。采用AdaBoost方法、Hough变换与直接最小二乘法拟合椭圆的方法确定眼睛的区域,并定位瞳孔与眼睑,根据五眼三庭知识得到人脸的区域,最后用AdaBoost Gabor滤波算法训练级联强分类器,并用此级联强分类器进行判别是否为人脸。在Yale、CMU Frontal Face等人脸库上进行实验,实验表明该方法不仅虚警率低,而且人脸检测率高。
Bibliography:51-1196/TP
YANG Ding-li, ZHANG Yu-lin, ZHOU Hong-biao, ZHAO Huan-yu, BAI Qiu-chan （ Faculty of Electronic ＆ Electrical Engineering, Huaiyin Institute of Technology, Huaian Jiangsu 223003, China）
eye location;Hough transform;direct least squares method;AdaBoost Gabor filter
Face detection rate is always affected by illumination. However the Gabor wavelet has good biological visual characteristic,and it is insensitive to illumination. In addition,if the position of the face was relatively fixed in images,the ability of the classifiers would be enhanced when classifiers were trained with Adaboost method. In order to increase the face detection rate when face image was affected by illumination,this paper proposed the new face detection method based on the human eye location and AdaBoost Gabor filter. Firstly,it determined eye region with AdaBoost method,Hough transform and direct least squares method. Secondly,it located the pupil and eyelid of the eye. Then,it obtained face region according to the knowledge of the
ISSN:1001-3695
DOI:10.3969/j.issn.1001-3695.2014.07.068