1、1-i 人脸识别算法人脸识别算法 The Design and Implementation of Algorithms for Human Face Recognition 1-ii 人脸识别算法 摘 要 人脸自动识别是模式识别领域的一项热门研究课题,有着十 分广泛的应用前景。本文对人脸位置矫正, 人脸的特征提取和识别 这些方面进行了研究,并提出了相应的实现算法。 人脸位置矫正作为人脸检测定位的一个环节,在计算机人脸 识别中具有重要的意义。本文第二章提出了一种基于单人脸灰度 图像中眼睛定位的人脸位置矫正方法,它是针对人眼灰度变化特 点、人眼几何形状特征及双眼的轴对称性而设计的。实验结果表 明
2、,该方法对于双眼可见单人脸灰度图像能实现快速有效矫正, 并能在矫正结果中精确给出双眼瞳孔位置。 本文第三章提出了一种基于神经网络的主元分析人脸图像识 别方法。该方法利用非线性主元分析神经网络对人脸图像提取人 脸特征(矢量),并在BP神经网络上实现了对人脸图像的识别。 实验结果证明了该方法的有效性和稳定性。 关键词 1-iii 人脸位置矫正,人脸特征提取,人脸识别,神经网络,灰度图像, 图像块纵向复杂度,主元分析法, 1-iv The Design and Implementation of Algorithms for Human Face Recognition Student: Yangb
3、o Gu Advisor: Dr. Wenming Cao Department of Computer Science and Technology College of Information Engineering Zhejiang University of Technology AbstractAbstract The automatic recognition of human faces is a hot spot in the field of pattern recognition , which has a wide range of potential applicati
4、ons . As the results of our in-depth research ,two algorithms are proposed : one for face pose adjustment , the other for facial feature extraction and face identification . Face pose adjustment , as a loop of human face location, is very important in computer face recognition. Chapter 2 of this thesis presents a new approach to automatic face pose adjustment on gray-scale static images with a single face . In a first stage , the right positions of eyes are precisely detected according to