【正文】 保 留其中的一部分生成低維的人臉空間，即人臉的特征子空間，識(shí)別時(shí)將測(cè)試圖像投影到此空間，得到一組投影系數(shù)，通過與各個(gè)人臉圖像比較進(jìn)行識(shí)別。主成分分析方法 (Principal Component Analysis ,PCA)，即離散 KL變換，是圖像壓縮中的一種最優(yōu)正交變換。本文介紹了幾種主要的預(yù)處理方法，如幾何歸一化，灰度歸一化。 首先描述了人臉識(shí)別技術(shù)的研究內(nèi)容、方法、應(yīng)用前景，對(duì)人臉自動(dòng)檢測(cè)與識(shí)別技術(shù)進(jìn)行了綜述。 I 內(nèi) 容 摘 要 生物特征識(shí)別是利用人類特有的生理或行為特征來識(shí)別個(gè)人身份的技術(shù)，它提供了一種高可靠性、高穩(wěn)定性的身份鑒別途徑。人臉檢測(cè)和識(shí)別是目前生物特征識(shí)別中最受人們關(guān)注的一個(gè)分支，是當(dāng)前圖像處理、模式識(shí)別和計(jì)算機(jī)視覺領(lǐng)域內(nèi)的一個(gè)熱門研究課題，在公安部門罪犯搜索、安全部門動(dòng)態(tài)監(jiān)視識(shí)別、銀行密碼系統(tǒng)等許多領(lǐng)域有廣泛的研究，本文對(duì)此進(jìn)行了較為深入的研究。并且詳細(xì)介紹了人臉識(shí)別很重要的一個(gè)步驟 — “人臉預(yù)處理”，文中提到的人 臉預(yù)處理方法都是從圖像處理的角度著手的，主要目的是使人臉圖像標(biāo)準(zhǔn)化，并在一定程度上消除光照的影響。 其次，本文重點(diǎn)描述了人臉識(shí)別的經(jīng)典方法， PCA方法。它用一個(gè)低維子空間來描述人臉圖像，同時(shí)又能在一定程度上保存所需要的識(shí)別信息。這種方法使得壓縮前后的均方誤差最小，且變換后的低維空間有很好的分辨能力。 關(guān)鍵詞 人臉識(shí)別 。主成分分析 II 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 puter vision. It is widely applied in mercial and law area, such as mug shots retrieval, realtine 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, grayscale normalization and images binaryconversion. Principal Component Analysis (PCA) face recognition methods as the foundation of the KL transformation is the most superior in the image pression .By using PCA, the dimension of the input is reduced while the main ponents are maintained. The major idea of PCA is to depose a data space into a linear bination of a small collection of the III facerecognition 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 paring the projection to all gallery images, and it causes around the pression the mean error to be youngest. But in the PCAbased 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 錄 IV 第一章 緒 論 ................................................................................................ 1 ............................................................................. 1 ............................................................... 3 ........................................................................................... 6 ............................................................................... 6 .......................................................................... 6 ........................................................ 7 KL 變換的特征臉方法 ............................................................ 9 ..................................................................................... 10 .............................................................. 12 ......................................................... 13 FISHER 線性判別式的方法 .................................................. 13 ................................................................... 14 ............................................................................................ 14 ....................................................... 15 ................................................................... 15 ....................................................................... 17 第二章人臉圖像預(yù)處理 .............................................................................. 18 .................................................................................................................... 18 ............................................................................................ 18 .............................................................................. 19 ............................................................................ 19 V ....................................................................... 20 .......................................................................................................... 23 第三章 基于 PCA的人臉識(shí)別方法 ............................................................. 23 .................................................................................................................... 23 PCA 人臉識(shí)別方法原理 .............................................................................. 23 ................................................................................. 24 KL 變換的原理 ....................................................................... 24 ..................................................................................... 26 ..........................................................27 PCA 人臉識(shí)別 .........