内容发布更新时间 : 2024/5/19 22:59:45星期一 下面是文章的全部内容请认真阅读。

内 容 摘 要

生物特征识别是利用人类特有的生理或行为特征来识别个人身份的技术，它提供了一种高可靠性、高稳定性的身份鉴别途径。人脸检测和识别是目前生物特征识别中最受人们关注的一个分支，是当前图像处理、模式识别和计算机视觉领域内的一个热门研究课题，在公安部门罪犯搜索、安全部门动态监视识别、银行密码系统等许多领域有广泛的研究，本文对此进行了较为深入的研究。

首先描述了人脸识别技术的研究内容、方法、应用前景，对人脸自动检测与识别技术进行了综述。并且详细介绍了人脸识别很重要的一个步骤—“人脸预处理”，文中提到的人脸预处理方法都是从图像处理的角度着手的，主要目的是使人脸图像标准化，并在一定程度上消除光照的影响。本文介绍了几种主要的预处理方法，如几何归一化，灰度归一化。

其次，本文重点描述了人脸识别的经典方法，PCA方法。主成分分析方法(Principal Component Analysis ,PCA)，即离散K-L变换，是图像压缩中的一种最优正交变换。它用一个低维子空间来描述人脸图像，同时又能在一定程度上保存所需要的识别信息。其基本原理为:由高维图像空间经K-L变换后得到一组新的正交基，对这些正交基作一定的取舍，保留其中的一部分生成低维的人脸空间，即人脸的特征子空间，识别时将测试图像投影到此空间，得到一组投影系数，通过与各个人脸图像比较进行识别。这种方法使得压缩前后的均方误差最小，且变换后的低维空间有很好的分辨能力。但在这种人脸识别技术中，二维的人脸图像矩阵必须先转化为一维的图像向量，才能进行PCA分析，而在这种转化后，造成图像向量的维数一般较高，使整个特征抽取过程所耗费的计算量相当可观。

关键词

人脸识别;人脸预处理;主成分分析

I

Research on Face Recognition Based on Principal Component Analysis

Abstract

Biometrics is a kind of science and technology using individual

physiological or behavioral characteristics to verify identity. It provides a highly reliable and robust approach to the identity recognition. Automatic face detection and recognition is one of the most attention branches of biometrics and it is also the one of the most active and challenging tasks for image processing, pattern recognition and computer vision. It is widely applied in commercial and law area, such as mug shots retrieval, real-tine video surveillance in security system and cryptography in bank and so on. The main research works and contributions are as the following.

First, the research content, approach and development are emphasized. The research status is introduced. The technology of the face detection and recognition are summarized. And the paper describes face preprocessing in detail which is and important step in the face recognition. The face preprocessing methods we adopt are based on image processing techniques. The main purpose is to get the standardized facial images, and to eliminate the impact of illumination to some extent. In this paper, several key preprocessing methods are introduced, such as geometry normalization, gray-scale normalization and images binary-conversion.

Principal Component Analysis (PCA) face recognition methods as the foundation of the K-L transformation is the most superior in the image compression .By using PCA, the dimension of the input is reduced while the main components are maintained. The major idea of PCA is to decompose a data space into a linear combination of a small collection of bases.In the

II

face-recognition literature, the eigenvectors can be referred to as eigenfaces. The probe is identified by first projection to all gallery images. We denote a probe .A probe is comparing the projection to all gallery images, and it causes around the compression the mean error to be youngest. But in the PCA-based face recognition technique, the 2D face image matrices must be previously transformed into 1 D image vectors. The resulting image vectors of faces usually lead to a high dimensional image vector space, where it is difficult to evaluate the covariance matrix accurately due to its large size and the relatively small number of training samples.

Key words

Face recognition ；Face pretreatment；PCA

目 录

III