人臉識別中若干特征優(yōu)化方法研究
發(fā)布時間：2018-10-17 19:45
【摘要】：隨著信息技術(shù)的快速發(fā)展,生物特征識別技術(shù)正在被大范圍地應(yīng)用到金融、安防等領(lǐng)域并受到了社會各界的廣泛認可。與其它生物特征識別技術(shù)相比,人臉識別技術(shù)具有友好、直觀、可靠等特點,所以人臉識別技術(shù)已成為生物特征識別技術(shù)中比較具有代表性的一項技術(shù)。人臉圖像易受光照、表情等因素的影響,因此在實際應(yīng)用中仍然存在很多挑戰(zhàn)。在人臉識別模型中涉及到圖像預(yù)處理、維數(shù)約簡以及分類判決三個主要組成部分,如何有效利用特征與分類器之間的關(guān)系,從而增強特征判別力并且提高特征簡潔度成為了當(dāng)前研究的熱點問題。本文從基于表示的分類器(Representation based Classifier,RC)角度出發(fā),在有監(jiān)督信號的情況下分別通過特征增強和特征提取方法實現(xiàn)了特征與分類器間的相互影響和相互制約。另外,本文以特征自表示模型為基礎(chǔ),通過特征間的線性表示及內(nèi)積約束等實現(xiàn)了無監(jiān)督的特征選擇。有關(guān)這三種特征優(yōu)化方法的具體工作總結(jié)如下:1.提出了一種新的濾波器學(xué)習(xí)方法,即基于表示的有監(jiān)督濾波器學(xué)習(xí)方法。該方法通過有針對性地學(xué)習(xí)得到濾波器,并使濾波后圖像的局部特征判別力增強,從而實現(xiàn)減小同一個人不同圖像間差異,并且增大不同人間圖像差異的目的。該方法的特點有:(1)在監(jiān)督信號下,從局部二值模式(Local Binary Pattern,LBP)角度出發(fā)設(shè)計濾波器,從而使濾波后圖像的LBP特征具有判別能力;(2)利用線性回歸方法刻畫圖像像素點間的類內(nèi)和類間表示誤差,并在線性判別分析的約束下得到濾波器,從而使濾波后特征在稀疏表示分類器和線性回歸分類器下得到更好的識別結(jié)果;(3)與采用固定模式的傳統(tǒng)濾波器(如均值濾波器)不同,該方法是在數(shù)據(jù)驅(qū)動情況下有針對性地學(xué)習(xí)濾波器;(4)在單模態(tài)和多模態(tài)人臉數(shù)據(jù)庫上均驗證了該方法的有效性。通過大量的實驗可以看出,該方法可以有效提高特征的判別力,并且在RC下可以得到更好的分類結(jié)果。2.結(jié)合字典學(xué)習(xí)提出了一種新的特征提取方法,即基于判別字典與投影聯(lián)合學(xué)習(xí)的稀疏表示分類方法。該方法通過同時學(xué)習(xí)帶有約束的字典和投影矩陣,不僅得到了更具表示力和判別力的字典,還得到了維數(shù)更低且更具判別力的特征,從而提升了人臉識別模型的分類性能。該方法的特點有:(1)通過對稀疏表示系數(shù)矩陣加入線性判別分析約束得到了具有判別能力的字典,并且通過對降維后樣本加入線性判別分析約束得到了具有判別能力的投影矩陣;(2)通過聯(lián)合學(xué)習(xí)使得字典和投影矩陣能夠更好地相互配合,進而得到更好的識別結(jié)果;(3)提出了一種有效的迭代優(yōu)化求解算法,并分別從理論分析和數(shù)值實驗兩方面驗證了算法的收斂性;(4)在人臉圖像和視頻數(shù)據(jù)庫上均驗證了該方法的有效性。通過大量的實驗可以看出,該方法可以有效提高特征簡潔度并增強特征的判別力,即使在訓(xùn)練樣本數(shù)較少的情況下仍然可以取得較好的識別性能。3.提出了一種新的無監(jiān)督特征選擇方法,即基于內(nèi)積正則化非負自表示模型的無監(jiān)督特征選擇方法。該方法通過特征自表示模型和內(nèi)積約束等去除了不相關(guān)特征及冗余特征,從而使特征子集具有較高的稀疏性和較低的冗余性。該方法的特點有:(1)利用特征的自表示模型來描述特征的顯著程度,從而獲得特征的權(quán)重矩陣;(2)采用內(nèi)積正則化對特征權(quán)重矩陣進行約束,由此可以獲得具有較高稀疏性和較低冗余性特點的特征子集;(3)采用非負約束對特征權(quán)重矩陣進行約束,從而保證所選特征的實際意義;(4)提出了一種有效的迭代優(yōu)化求解算法,并分別從理論分析和數(shù)值實驗兩方面驗證了算法的收斂性。實驗結(jié)果表明該方法不僅可以有效提高特征的簡潔度,而且可以得到更好的分類和聚類結(jié)果。綜上所述,本文主要圍繞人臉識別模型中特征優(yōu)化問題展開了廣泛而深入地研究,針對如何增強局部特征(LBP)的判別力、如何通過學(xué)習(xí)投影矩陣提高特征的簡潔度和判別力以及如何提高特征子集有效性的問題,分別提出了三種特征優(yōu)化方法。從實驗結(jié)果可以看出,本文提出的方法對人臉識別研究有一定的推動作用并具有較好的應(yīng)用前景。
[Abstract]:With the rapid development of information technology, biometric identification technology is being widely applied to finance, security and other fields and is widely recognized by all circles of society. Compared with other biometric identification technologies, face recognition technology has the characteristics of friendship, intuition, reliability and so on, so the face recognition technology has become a representative technique in biological feature recognition technology. Face images are easy to be influenced by light, expression and other factors, so there are still many challenges in practical application. In the face recognition model, three main components of image preprocessing, dimension reduction and classification decision are involved, how to effectively utilize the relationship between feature and classifier, so that the characteristic discrimination force is enhanced and the characteristic simplicity is improved to become the hot issue of the current research. Based on the representation based classifier (RC), the interaction and mutual restriction between the feature and the classifier are realized by feature enhancement and feature extraction. In addition, based on the feature self-representation model, the feature-free feature selection is realized through linear representation and inner product constraint among features. Specific work on these three feature optimization methods is summarized as follows: 1. A new method of filter learning is proposed, which is based on the representation of supervised filter learning method. the method achieves the purpose of reducing the difference between different images of the same person and increasing the difference between different human images by carrying out targeted learning to obtain a filter and enhancing the local characteristic discrimination force of the filtered image. The method is characterized in that: (1) under the supervision signal, the filter is designed from the local binary pattern (LBP) angle, so that the LBP characteristic of the filtered image has the discrimination ability; (2) using the linear regression method to depict the intra-class and inter-class representation errors among image pixel points, and obtaining a filter under the constraint of linear discriminant analysis, so that the filtered features obtain better recognition results under sparse representation classifier and linear regression classifier; (3) Different from the traditional filter with fixed mode (such as the mean filter), the method is to study the filter with pertinence under the condition of data driving, and (4) the validity of the method is verified on the single mode and the multi-modal face database. As can be seen from a large number of experiments, the method can effectively improve the distinguishing force of the characteristic, and can obtain better classification result under the RC. A new feature extraction method is proposed in combination with dictionary learning, which is based on the sparse representation classification method of discrimination dictionary and projection joint learning. By studying the dictionary and the projection matrix with constraints at the same time, the method not only obtains the dictionary which is more representative of the force and the discrimination force, but also obtains the feature of lower dimension number and more discriminating force, thereby improving the classification performance of the face recognition model. The method is characterized in that: (1) a dictionary with discrimination capability is obtained by adding a linear discriminant analysis constraint to a sparse representation coefficient matrix, and a projection matrix with discrimination capability is obtained by adding linear discriminant analysis constraint to the reduced-dimensional post-sample; (2) through joint learning, the dictionary and the projection matrix can be better matched with each other so as to obtain better recognition results; (3) an effective iterative optimization solution algorithm is proposed, and the convergence of the algorithm is verified from two aspects of theoretical analysis and numerical experiment, respectively; (4) The validity of the method is verified on the face image and the video database. As can be seen from a large number of experiments, the method can effectively improve the characteristic simplicity and enhance the distinguishing force of the characteristic, and even if the number of the training samples is small, better identification performance can be obtained. A new non-supervised feature selection method is proposed, i.e., the non-supervised feature selection method based on inner product regularization non-negative self-representation model. According to the method, the feature self-representation model and the inner product constraint are used to remove irrelevant features and redundant characteristics, so that the feature subsets have higher sparsity and lower redundancy. The method is characterized in that: (1) a characteristic self-representation model is utilized to describe the salient extent of the feature so as to obtain a weight matrix of the feature; and (2) the feature weight matrix is constrained by using the inner product regularization, therefore, a feature subset with higher sparsity and lower redundancy characteristics can be obtained; (3) a feature weight matrix is constrained by adopting a non-negative constraint, so that the practical significance of the selected feature is ensured; and (4) an efficient iterative optimization solution algorithm is proposed, The convergence of the algorithm is verified from both theoretical and numerical experiments. The experimental results show that the method not only can effectively improve the simplicity of the feature, but also can obtain better classification and clustering results. To sum up, this paper mainly studies the feature optimization problem in face recognition model, and aims at how to enhance the distinguishing force of local feature (LBP). How to improve the simplicity and discrimination of the feature by studying the projection matrix and how to improve the effectiveness of the feature subset are presented. It can be seen from the experimental results that the method proposed in this paper has a certain promoting effect on face recognition research and has a good application prospect.
【學(xué)位授予單位】：東北師范大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2017
【分類號】：TP391.41
本文編號：2277760
[Abstract]:With the rapid development of information technology, biometric identification technology is being widely applied to finance, security and other fields and is widely recognized by all circles of society. Compared with other biometric identification technologies, face recognition technology has the characteristics of friendship, intuition, reliability and so on, so the face recognition technology has become a representative technique in biological feature recognition technology. Face images are easy to be influenced by light, expression and other factors, so there are still many challenges in practical application. In the face recognition model, three main components of image preprocessing, dimension reduction and classification decision are involved, how to effectively utilize the relationship between feature and classifier, so that the characteristic discrimination force is enhanced and the characteristic simplicity is improved to become the hot issue of the current research. Based on the representation based classifier (RC), the interaction and mutual restriction between the feature and the classifier are realized by feature enhancement and feature extraction. In addition, based on the feature self-representation model, the feature-free feature selection is realized through linear representation and inner product constraint among features. Specific work on these three feature optimization methods is summarized as follows: 1. A new method of filter learning is proposed, which is based on the representation of supervised filter learning method. the method achieves the purpose of reducing the difference between different images of the same person and increasing the difference between different human images by carrying out targeted learning to obtain a filter and enhancing the local characteristic discrimination force of the filtered image. The method is characterized in that: (1) under the supervision signal, the filter is designed from the local binary pattern (LBP) angle, so that the LBP characteristic of the filtered image has the discrimination ability; (2) using the linear regression method to depict the intra-class and inter-class representation errors among image pixel points, and obtaining a filter under the constraint of linear discriminant analysis, so that the filtered features obtain better recognition results under sparse representation classifier and linear regression classifier; (3) Different from the traditional filter with fixed mode (such as the mean filter), the method is to study the filter with pertinence under the condition of data driving, and (4) the validity of the method is verified on the single mode and the multi-modal face database. As can be seen from a large number of experiments, the method can effectively improve the distinguishing force of the characteristic, and can obtain better classification result under the RC. A new feature extraction method is proposed in combination with dictionary learning, which is based on the sparse representation classification method of discrimination dictionary and projection joint learning. By studying the dictionary and the projection matrix with constraints at the same time, the method not only obtains the dictionary which is more representative of the force and the discrimination force, but also obtains the feature of lower dimension number and more discriminating force, thereby improving the classification performance of the face recognition model. The method is characterized in that: (1) a dictionary with discrimination capability is obtained by adding a linear discriminant analysis constraint to a sparse representation coefficient matrix, and a projection matrix with discrimination capability is obtained by adding linear discriminant analysis constraint to the reduced-dimensional post-sample; (2) through joint learning, the dictionary and the projection matrix can be better matched with each other so as to obtain better recognition results; (3) an effective iterative optimization solution algorithm is proposed, and the convergence of the algorithm is verified from two aspects of theoretical analysis and numerical experiment, respectively; (4) The validity of the method is verified on the face image and the video database. As can be seen from a large number of experiments, the method can effectively improve the characteristic simplicity and enhance the distinguishing force of the characteristic, and even if the number of the training samples is small, better identification performance can be obtained. A new non-supervised feature selection method is proposed, i.e., the non-supervised feature selection method based on inner product regularization non-negative self-representation model. According to the method, the feature self-representation model and the inner product constraint are used to remove irrelevant features and redundant characteristics, so that the feature subsets have higher sparsity and lower redundancy. The method is characterized in that: (1) a characteristic self-representation model is utilized to describe the salient extent of the feature so as to obtain a weight matrix of the feature; and (2) the feature weight matrix is constrained by using the inner product regularization, therefore, a feature subset with higher sparsity and lower redundancy characteristics can be obtained; (3) a feature weight matrix is constrained by adopting a non-negative constraint, so that the practical significance of the selected feature is ensured; and (4) an efficient iterative optimization solution algorithm is proposed, The convergence of the algorithm is verified from both theoretical and numerical experiments. The experimental results show that the method not only can effectively improve the simplicity of the feature, but also can obtain better classification and clustering results. To sum up, this paper mainly studies the feature optimization problem in face recognition model, and aims at how to enhance the distinguishing force of local feature (LBP). How to improve the simplicity and discrimination of the feature by studying the projection matrix and how to improve the effectiveness of the feature subset are presented. It can be seen from the experimental results that the method proposed in this paper has a certain promoting effect on face recognition research and has a good application prospect.
【學(xué)位授予單位】：東北師范大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2017
【分類號】：TP391.41
【參考文獻】
相關(guān)期刊論文 前7條
1 張文超;山世光;張洪明;陳杰;陳熙霖;高文;;基于局部Gabor變化直方圖序列的人臉描述與識別[J];軟件學(xué)報;2006年12期
2 李武軍;王崇駿;張煒;陳世福;;人臉識別研究綜述[J];模式識別與人工智能;2006年01期
3 崔國勤,高文;基于雙層虛擬視圖和支持向量的人臉識別方法[J];計算機學(xué)報;2005年03期
4 張曉華,山世光,曹波,高文,周德龍,趙德斌;CAS-PEAL大規(guī)模中國人臉圖像數(shù)據(jù)庫及其基本評測介紹[J];計算機輔助設(shè)計與圖形學(xué)學(xué)報;2005年01期
5 張翠平,蘇光大;人臉識別技術(shù)綜述[J];中國圖象圖形學(xué)報;2000年11期
6 周杰,盧春雨,張長水,李衍達;人臉自動識別方法綜述[J];電子學(xué)報;2000年04期
7 陳彬，洪家榮，王亞東;最優(yōu)特征子集選擇問題[J];計算機學(xué)報;1997年02期
相關(guān)博士學(xué)位論文 前4條
1 孫宇平;基于稀疏表征和自相似性的視覺數(shù)據(jù)識別關(guān)鍵技術(shù)及應(yīng)用[D];華南理工大學(xué);2015年
2 王建中;基于流形學(xué)習(xí)的數(shù)據(jù)降維方法及其在人臉識別中的應(yīng)用[D];東北師范大學(xué);2010年
3 山世光;人臉識別中若干關(guān)鍵問題的研究[D];中國科學(xué)院研究生院（計算技術(shù)研究所）;2004年
4 張麗新;高維數(shù)據(jù)的特征選擇及基于特征選擇的集成學(xué)習(xí)研究[D];清華大學(xué);2004年
相關(guān)碩士學(xué)位論文 前2條
1 邱敏娜;基于樣本擴充的小樣本人臉識別研究[D];哈爾濱工業(yè)大學(xué);2014年
2 王海珍;基于LDA的人臉識別技術(shù)研究[D];西安電子科技大學(xué);2010年
，本文編號：2277760
本文鏈接：http://www.sikaile.net/kejilunwen/ruanjiangongchenglunwen/2277760.html
最近更新
教材專著
