基于PCA和SVM的人臉識(shí)別關(guān)鍵技術(shù)研究與實(shí)現(xiàn)
發(fā)布時(shí)間：2019-03-05 11:29
【摘要】：人臉識(shí)別作為當(dāng)今科研領(lǐng)域最熱門的課題之一,它的應(yīng)用已經(jīng)深入到了金融系統(tǒng)、信息安全、公共安全等各個(gè)領(lǐng)域。橫向?qū)Ρ葋砜?人臉識(shí)別在眾多模式識(shí)別方式中優(yōu)勢(shì)明顯,具有自然性、非侵?jǐn)_性、采集成本低以及人機(jī)交互性強(qiáng)的天然優(yōu)勢(shì),應(yīng)用場(chǎng)景更加廣闊�？v向分析,各大上市公司不斷推出大量商業(yè)化人臉識(shí)別產(chǎn)品,人臉識(shí)別將在未來呈現(xiàn)爆發(fā)式的增長(zhǎng)。因而研究人臉識(shí)別具有重大的現(xiàn)實(shí)意義。本文重點(diǎn)研究了人臉預(yù)處理、人臉特征提取和人臉識(shí)別這三大內(nèi)容。尤其是對(duì)主成分分析(Principal Component Analysis,PCA)和支持向量機(jī)(Support Vector Machines,SVM)算法進(jìn)行了深入的研究,并針對(duì)其并未利用類別信息的不足,引入了線性判別分析(Linear Discriminant Analysis,LDA),提出了基于PCA和SVM的人臉識(shí)別改進(jìn)框架,并基于改進(jìn)后的框架,實(shí)現(xiàn)了一個(gè)實(shí)時(shí)人臉識(shí)別系統(tǒng)。本文的主要工作有以下五個(gè)部分。(1)研究了多種常用的人臉圖像預(yù)處理技術(shù),包括彩色圖像的灰度化、圖像的灰度變化、直方圖均衡化及幾何歸一化等方法。人臉圖像預(yù)處理技術(shù)降低了外界因素,如光照、姿態(tài)、拍攝角度等問題對(duì)圖像的影響,實(shí)現(xiàn)了圖像的標(biāo)準(zhǔn)化處理,為之后的人臉識(shí)別工作的開展奠定了良好的基礎(chǔ)。最后,利用Matlab做了相關(guān)的算法檢驗(yàn)工作。(2)深入研究了基于PCA的人臉識(shí)別的理論基礎(chǔ)和具體的實(shí)施過程。由于在PCA算法中直接計(jì)算協(xié)方差矩陣的特征值和特征向量計(jì)算量太大,所以引入了SVD定理,實(shí)現(xiàn)了主元子空間的間接運(yùn)算。并利用Matlab進(jìn)行了大量的實(shí)驗(yàn),對(duì)PCA算法的優(yōu)劣進(jìn)行了分析,得出PCA算法具有良好降維效果,但并沒有分類的效果。(3)深入研究了線性支持向量機(jī)的理論基礎(chǔ),論述了SVM的分類器在小樣本以及學(xué)習(xí)等方面的優(yōu)點(diǎn)。然后運(yùn)用核函數(shù),將線性支持向量機(jī)擴(kuò)展成非線性支持向量機(jī),使得支持向量機(jī)能夠滿足人臉識(shí)別的分類要求。討論SVM多分類方法的實(shí)現(xiàn)。(4)針對(duì)PCA算法中并未利用分類信息的問題,引入線性判別分析,并提出基于PCA和SVM的人臉識(shí)別改進(jìn)框架,最終形成了PCA+LDA+SVM的人臉識(shí)別框架,并在Matlab平臺(tái)上經(jīng)過大量的實(shí)驗(yàn),探討了維數(shù)比率、訓(xùn)練樣本數(shù)目對(duì)算法的影響,驗(yàn)證了它良好分類效果。(5)基于改進(jìn)的人臉識(shí)別框架,用Visual Studio 2010、Open CV庫以及Qt框架實(shí)現(xiàn)了一個(gè)實(shí)時(shí)人臉識(shí)別系統(tǒng)。通過動(dòng)態(tài)人臉識(shí)別的測(cè)試,識(shí)別率為97.3%,識(shí)別效果優(yōu)良,每次的識(shí)別時(shí)間平均為356毫秒,滿足實(shí)時(shí)性的要求。
[Abstract]:Face recognition is one of the most popular topics in the field of scientific research. It has been applied in many fields, such as financial system, information security, public security and so on. In horizontal comparison, face recognition has obvious advantages in many pattern recognition methods, such as naturalness, non-intrusiveness, low collection cost and strong man-machine interaction, so the application scene is wider. Longitudinal analysis, the major listed companies continue to launch a large number of commercial face recognition products, face recognition will show explosive growth in the future. Therefore, the study of face recognition has great practical significance. This paper focuses on face preprocessing, face feature extraction and face recognition. Especially, the principal component analysis (Principal Component Analysis,PCA) and support vector machine (Support Vector Machines,SVM) algorithms are studied in depth, and the linear discriminant analysis (Linear Discriminant Analysis,LDA) is introduced to solve the problem that the class information is not utilized. An improved framework of face recognition based on PCA and SVM is proposed, and a real-time face recognition system is implemented based on the improved framework. The main work of this paper includes the following five parts: (1) A variety of pre-processing techniques of face image are studied, including grayscale of color image, gray level change of image, histogram equalization and geometric normalization and so on. Face image pre-processing technology reduces the influence of external factors, such as illumination, pose, shooting angle and so on, and realizes the standardized processing of face image, which lays a good foundation for the development of face recognition work. Finally, the related algorithms are tested by Matlab. (2) the theoretical basis and implementation process of face recognition based on PCA are deeply studied. Because the computation of eigenvalues and Eigenvectors of covariance matrix is too large in PCA algorithm, the SVD theorem is introduced to realize the indirect operation of principal subspace. A large number of experiments are carried out with Matlab, and the advantages and disadvantages of PCA algorithm are analyzed. It is concluded that PCA algorithm has good dimensionality reduction effect, but it has no effect of classification. (3) the theoretical basis of linear support vector machine is deeply studied. The advantages of SVM classifier in small samples and learning are discussed. Then the kernel function is used to extend the linear support vector machine to the nonlinear support vector machine, so that the support vector machine can meet the classification requirements of face recognition. The implementation of SVM multi-classification method is discussed. (4) aiming at the problem that the classification information is not used in PCA algorithm, linear discriminant analysis is introduced, and an improved framework of face recognition based on PCA and SVM is proposed. Finally, a face recognition framework of PCA LDA SVM is formed. Through a large number of experiments on Matlab platform, the influence of dimension ratio and number of training samples on the algorithm is discussed, and its good classification effect is verified. (5) based on the improved face recognition framework, Visual Studio 2010, A real-time face recognition system is implemented based on Open CV library and Qt framework. Through the test of dynamic face recognition, the recognition rate is 97.3%, and the recognition effect is good. The average recognition time is 356 milliseconds each time, which meets the real-time requirement.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41
本文編號(hào)：2434856
[Abstract]:Face recognition is one of the most popular topics in the field of scientific research. It has been applied in many fields, such as financial system, information security, public security and so on. In horizontal comparison, face recognition has obvious advantages in many pattern recognition methods, such as naturalness, non-intrusiveness, low collection cost and strong man-machine interaction, so the application scene is wider. Longitudinal analysis, the major listed companies continue to launch a large number of commercial face recognition products, face recognition will show explosive growth in the future. Therefore, the study of face recognition has great practical significance. This paper focuses on face preprocessing, face feature extraction and face recognition. Especially, the principal component analysis (Principal Component Analysis,PCA) and support vector machine (Support Vector Machines,SVM) algorithms are studied in depth, and the linear discriminant analysis (Linear Discriminant Analysis,LDA) is introduced to solve the problem that the class information is not utilized. An improved framework of face recognition based on PCA and SVM is proposed, and a real-time face recognition system is implemented based on the improved framework. The main work of this paper includes the following five parts: (1) A variety of pre-processing techniques of face image are studied, including grayscale of color image, gray level change of image, histogram equalization and geometric normalization and so on. Face image pre-processing technology reduces the influence of external factors, such as illumination, pose, shooting angle and so on, and realizes the standardized processing of face image, which lays a good foundation for the development of face recognition work. Finally, the related algorithms are tested by Matlab. (2) the theoretical basis and implementation process of face recognition based on PCA are deeply studied. Because the computation of eigenvalues and Eigenvectors of covariance matrix is too large in PCA algorithm, the SVD theorem is introduced to realize the indirect operation of principal subspace. A large number of experiments are carried out with Matlab, and the advantages and disadvantages of PCA algorithm are analyzed. It is concluded that PCA algorithm has good dimensionality reduction effect, but it has no effect of classification. (3) the theoretical basis of linear support vector machine is deeply studied. The advantages of SVM classifier in small samples and learning are discussed. Then the kernel function is used to extend the linear support vector machine to the nonlinear support vector machine, so that the support vector machine can meet the classification requirements of face recognition. The implementation of SVM multi-classification method is discussed. (4) aiming at the problem that the classification information is not used in PCA algorithm, linear discriminant analysis is introduced, and an improved framework of face recognition based on PCA and SVM is proposed. Finally, a face recognition framework of PCA LDA SVM is formed. Through a large number of experiments on Matlab platform, the influence of dimension ratio and number of training samples on the algorithm is discussed, and its good classification effect is verified. (5) based on the improved face recognition framework, Visual Studio 2010, A real-time face recognition system is implemented based on Open CV library and Qt framework. Through the test of dynamic face recognition, the recognition rate is 97.3%, and the recognition effect is good. The average recognition time is 356 milliseconds each time, which meets the real-time requirement.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前9條
1 趙思陽;張衛(wèi)華;周激流;;基于多重流形嵌入的局部線性嵌入與等距映射面部表情估計(jì)方法[J];計(jì)算機(jī)應(yīng)用;2016年S2期
2 丁賓;王陽生;楊明浩;姚健;;從多張非標(biāo)定圖像重建三維人臉[J];計(jì)算機(jī)輔助設(shè)計(jì)與圖形學(xué)學(xué)報(bào);2010年02期
3 馮元戩,施鵬飛;基于支持向量機(jī)的彩色圖像人臉檢測(cè)方法[J];上海交通大學(xué)學(xué)報(bào);2003年06期
4 王守覺;仿生模式識(shí)別(拓?fù)淠Ｊ阶R(shí)別)——一種模式識(shí)別新模型的理論與應(yīng)用[J];電子學(xué)報(bào);2002年10期
5 梁路宏,艾海舟,徐光佑,張鈸;基于模板匹配與人工神經(jīng)網(wǎng)確認(rèn)的人臉檢測(cè)[J];電子學(xué)報(bào);2001年06期
6 賴劍煌,阮邦志,馮國燦;頻譜臉:一種基于小波變換和Fourier變換的人像識(shí)別新方法[J];中國圖象圖形學(xué)報(bào);1999年10期
7 楊光正;黃熙濤;;鑲嵌圖在人面定位中的應(yīng)用[J];模式識(shí)別與人工智能;1996年03期
8 洪子泉，，楊靜宇;基于奇異值特征和統(tǒng)計(jì)模型的人像識(shí)別算法[J];計(jì)算機(jī)研究與發(fā)展;1994年03期
9 張廣鵬;王蘊(yùn)紅;張兆翔;;基于多模態(tài)人臉與人耳融合的身份識(shí)別與認(rèn)證[J];高技術(shù)通訊;2011年07期
相關(guān)碩士學(xué)位論文 前9條
1 張利芳;基于PCA算法的人臉識(shí)別系統(tǒng)研究[D];中北大學(xué);2015年
2 葉超;基于Gabor小波和SVM的人臉識(shí)別算法研究[D];中北大學(xué);2014年
3 楊峰;基于支持向量機(jī)的車身顏色識(shí)別方法研究[D];電子科技大學(xué);2013年
4 謝春華;基于人臉圖像的年齡估計(jì)方法研究[D];電子科技大學(xué);2013年
5 黃泉龍;基于PCA的人臉識(shí)別研究[D];西安電子科技大學(xué);2012年
6 王本超;基于KPCA與SVM的人臉識(shí)別研究[D];大連理工大學(xué);2010年
7 王海珍;基于LDA的人臉識(shí)別技術(shù)研究[D];西安電子科技大學(xué);2010年
8 左登宇;基于Adaboost算法的人臉檢測(cè)研究[D];中國科學(xué)技術(shù)大學(xué);2009年
9 齊興敏;基于PCA的人臉識(shí)別技術(shù)的研究[D];武漢理工大學(xué);2007年
本文編號(hào)：2434856
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2434856.html
最近更新
教材專著
