摘要
目前的人脸检测方法多是针对正面人脸,而对于多视角人脸检测还存在很大困难,有效的方法还不多。本文考虑到人脸检测中旋转人脸和侧面人脸两种多视角情况,提出了一种多视角人脸检测方法。针对平面内旋转的问题,在YCbCr色彩空间内建立肤色模型,经过处理确定人脸椭圆区域,利用基于灰度加权的主成分分析算法进行人脸的角度校正,得到偏转校正后的人脸图像。针对侧面人脸的问题,通过上下和左右2个方向的人脸旋转样本库来训练分类器,然后组合成并联分类器,再对偏转校正后的人脸图像进行人脸验证。实验结果表明,该方法可以对任意视角的人脸进行有效的检测,且有较高的检测率。
The current method for the detection of human faces is mostly the frontalview detection, while the multiview detection is still difficult, with few effective methods. Considering the rotation face and side face, this paper presents a multiview face detection method. For rotating on the plane, we generate a human skin model in the YCbCr color space. After treatment, the elliptic color area of face is determined. Then, using the gray weighting of the principal component analysis algorithm for angle correction,we obtain the correction face image. For the side face, through the face set of two directions of up or down and left or right, we train the classifier, and combine them into a parallel connection classifier for validation. Experiments prove that this method is adaptive to different viewpoint face and has a high face detection rate.
出处
《计算机工程与科学》
CSCD
北大核心
2011年第1期132-137,共6页
Computer Engineering & Science
基金
辽宁省高校重点实验室基金资助项目(2008S115)
关键词
人脸检测
多视角
肤色模型
角度校正
并联分类器
face detection
multi-view
skin model
angularity correction
parallel connection classifier
