本文選題：人臉識(shí)別 + 稀疏表示�。� 參考：《山東大學(xué)》2016年博士論文

【摘要】：作為一種生物特征,人臉具有可隨身攜帶、不會(huì)丟失、不易被盜取等優(yōu)點(diǎn),而且人臉圖像采集方式友好、無需配合甚至具有隱蔽性�；谌四樀纳矸葑R(shí)別將成為未來身份認(rèn)證和識(shí)別的主流方法,在經(jīng)濟(jì)、民用、軍用、公安等領(lǐng)域具有廣闊的應(yīng)用前景,是當(dāng)前基于生物特征身份識(shí)別領(lǐng)域中的研究熱點(diǎn)。目前非限制條件下的人臉識(shí)別技術(shù)還不完善,還需進(jìn)行深入研究并提出高效的識(shí)別算法。稀疏表示算法具有較高的分類性能,在圖像分類及模式識(shí)別領(lǐng)域得到了廣泛研究和應(yīng)用。構(gòu)造過完備冗余字典和稀疏表示矢量的快速求解是稀疏表示理論應(yīng)用中的兩大問題。論文針對(duì)人臉識(shí)別這一典型的小樣本問題,圍繞基于訓(xùn)練人臉圖像的冗余字典構(gòu)造方法、稀疏表示矢量的快速求解算法以及進(jìn)一步提高稀疏表示分類性能等問題展開了以下研究工作。(1)提出利用位平面圖像協(xié)作表示分類投票決策的人臉識(shí)別算法。研究了正則化最小二乘協(xié)作表示(CRC_RLS)分類算法的原理,分析了其與稀疏表示分類(SRC)的區(qū)別與聯(lián)系以及它們?cè)谧R(shí)別性能上的差異,在此基礎(chǔ)上提出利用人臉圖像的位平面信息和投票決策算法對(duì)協(xié)作表示算法進(jìn)行改進(jìn),以提高協(xié)作表示分類算法的準(zhǔn)確性和稀疏表示算法的識(shí)別速度。為突出人臉圖像的輪廓,增強(qiáng)圖像中的識(shí)別信息,本算法采用累積分布函數(shù)對(duì)圖像進(jìn)行直方圖均衡。對(duì)均衡圖像進(jìn)行位平面分解,得到包含不同類別信息的多個(gè)二進(jìn)制位平面圖像,同一位平面圖像構(gòu)成同一位平面數(shù)據(jù)庫。本文采用256級(jí)灰度圖像進(jìn)行實(shí)驗(yàn),一幅人臉圖像可分解出8幅位平面圖像,一個(gè)灰度人臉圖像庫擴(kuò)展為8個(gè)不同位平面人臉圖像庫。利用協(xié)作表示分類算法分別訓(xùn)練出每個(gè)位平面的正確識(shí)別率。實(shí)驗(yàn)證明圖像均衡后,第2個(gè)位平面和第8個(gè)位平面具有相同的正確識(shí)別率,第3和第4位平面的正確識(shí)別率均在0.25以下。選擇正確識(shí)別率較高的1、5、6、7、8等5個(gè)位平面,分別利用協(xié)作表示算法對(duì)輸入圖像進(jìn)行識(shí)別。采用“最高票當(dāng)選”制對(duì)5個(gè)識(shí)別結(jié)果進(jìn)行投票。當(dāng)多數(shù)投票結(jié)果不唯一時(shí),定義為投票決策失敗,進(jìn)行二次判決：利用各位平面圖像構(gòu)造虛擬加權(quán)圖像,在虛擬加權(quán)圖像庫上再次利用協(xié)作表示算法對(duì)圖像進(jìn)行分類。利用二進(jìn)制位平面圖像代替二值灰度位平面圖像,避免了在虛擬加權(quán)人臉圖像中低位平面被高位平面“淹沒”的問題,權(quán)重系數(shù)由位平面的“位序數(shù)”和“正確識(shí)別率”共同確定,既保證了不同位平面具有不同的權(quán)重,又限制了高、低位平面的權(quán)重差值不會(huì)過大。在ORL和FERET人臉庫上,正確識(shí)別率分別為97%和98%,與CRC_RLS算法相比,均提高了4%。與SRC算法相比,分別提高了4%和2%。訓(xùn)練圖像的位平面分解、權(quán)重系數(shù)的訓(xùn)練與虛擬加權(quán)訓(xùn)練圖像的構(gòu)造均在訓(xùn)練階段完成,不會(huì)影響實(shí)時(shí)人臉識(shí)別速度,因此識(shí)別速度與CRC_RLS相當(dāng),比SRC算法的識(shí)別速度提高了10倍以上。(2)提出基于局部構(gòu)造模式近鄰樣本協(xié)作表示的人臉識(shí)別算法。隨著字典原子數(shù)量增多,稀疏表示矢量的求解復(fù)雜度急劇上升,從而引起識(shí)別速度下降,同時(shí)字典原子與測(cè)試圖像在結(jié)構(gòu)上的相似度越高,正確識(shí)別率也越高。論文提出一種基于LCP特征的自適應(yīng)字典學(xué)習(xí)算法,利用該字典對(duì)測(cè)試圖像進(jìn)行協(xié)作表示分類,既提高了識(shí)別速度,又提高了正確識(shí)別率。LCP特征包含局部結(jié)構(gòu)(LBP)和局部微觀構(gòu)造(Mic)兩層特征。本算法提出利用卡方系數(shù)的負(fù)對(duì)數(shù)定義基于歸一化直方圖卡方距離的“x2-LBP-相似性,,和基于bin-比例直方圖距離的‘'χ2-BRD-LBP-相似性”,用以衡量圖像在LBP特征層的相似程度,采用歐氏距離判斷圖像在微觀構(gòu)造特征層上的相似度(MiC-相似性),通過大量實(shí)驗(yàn)給出了χ2 -LBP-相似性和χ2-BRD-LBP-相似性的合法閾值、近鄰閾值以及MiC-相似性的合法閾值、近鄰閾值的經(jīng)驗(yàn)取值范圍。詳細(xì)分析討論了直方圖特征與MiC特征級(jí)聯(lián)／并聯(lián)、bin-比例直方圖特征與MiC特征級(jí)聯(lián)／并聯(lián)四種融合方法下錯(cuò)誤拒絕識(shí)別、錯(cuò)誤接收識(shí)別以及近鄰樣本選擇三個(gè)問題。聯(lián)合LBP特征和Mic特征,確定圖像在LCP特征上的相似性,并根據(jù)預(yù)先設(shè)定的近鄰閾值自適應(yīng)地選擇近鄰樣本,構(gòu)造冗余字典。本算法提出的冗余字典的原子數(shù)量降到了訓(xùn)練圖像數(shù)量的2/3以下,而且原子結(jié)構(gòu)與測(cè)試樣本的結(jié)構(gòu)具有更高的相似性,正確識(shí)別率得到提高�；诒壤狈綀D自適應(yīng)構(gòu)造的冗余字典對(duì)有遮擋圖像的分類具有更高的魯棒性。在ORL、FERET、YaleB和AR人臉庫上,無遮擋識(shí)別時(shí),本算法比SRC RLC的正確識(shí)別率提高了3%左右,利用AR庫進(jìn)行圍巾和墨鏡遮擋實(shí)驗(yàn),正確識(shí)別率可達(dá)到85%。(3)提出利用Gabor近鄰和壓縮感知降維進(jìn)行稀疏表示分類的人臉識(shí)別算法。人臉識(shí)別屬于典型的小樣本問題,利用人臉圖像作為原子構(gòu)造的字典不滿足原子數(shù)量大于特征數(shù)量的條件,以上兩種算法在使用協(xié)作表示分類之前,首先對(duì)圖像進(jìn)行PCA降維以滿足字典要求,特征選擇的問題依然存在。若采用壓縮感知對(duì)人臉圖像進(jìn)行降維,則可避免特征選擇難題,克服人臉識(shí)別中的小樣本問題。本算法提取人臉圖像的低維Gabor特征,在Gabor特征空間,利用相關(guān)系數(shù)自動(dòng)尋找測(cè)試樣本的近鄰并作為表示基構(gòu)成表示矩陣。通過大量實(shí)驗(yàn)證明了合法數(shù)據(jù)與訓(xùn)練樣本的平均相關(guān)系數(shù)不依賴于具體的測(cè)試樣本,并給出合法測(cè)試數(shù)據(jù)相關(guān)系數(shù)閾值的經(jīng)驗(yàn)值。對(duì)合法測(cè)試數(shù)據(jù),以“類平均相關(guān)系數(shù)”為準(zhǔn)則選擇近鄰樣本并構(gòu)成表示矩陣,表示基涵蓋了訓(xùn)練樣本的全部類別,同時(shí)表示矩陣中表示基的數(shù)量減少了一半,而且表示基和測(cè)試圖像具有更高的結(jié)構(gòu)相似性,更符合壓縮感知理論對(duì)于表示矩陣的要求。采用隨機(jī)分布的高斯矩陣作為感知矩陣對(duì)人臉圖像進(jìn)行感知,將高維人臉圖像投影到任意低維的觀測(cè)空間上進(jìn)行識(shí)別。分別采用正交匹配跟蹤算法(OMP)和線性規(guī)劃優(yōu)化算法求稀疏表示矢量,并逐類完成測(cè)試樣本的種屬判決。與SRC算法相比,識(shí)別速度提高了5倍,在無遮擋的識(shí)別中,正確識(shí)別率提高了5%,對(duì)于AR庫上的圍巾遮擋和墨鏡遮擋,正確識(shí)別率提高了將近1倍,分別達(dá)到83%和73%。
[Abstract]:As a biological feature, human faces have the advantages of portable, not lost and uneasy to be stolen, and face image acquisition is friendly, without coordination or even concealment. Face based identification will become the mainstream method of identification and identification in the future, and it is widely used in the fields of economy, civil, military, public security and so on. With the prospect, it is a hot topic in the field of biometric identification. At present, the face recognition technology under non restrictive conditions is not perfect. It needs to be studied and put forward the efficient recognition algorithm. The sparse representation algorithm has high classification performance. It has been widely studied and applied in the field of image classification and pattern recognition. The two major problems in sparse representation are constructed over complete redundant dictionaries and sparse representation vectors. This paper focuses on the typical small sample problem of face recognition. This paper focuses on the redundant dictionary construction method based on training face images, fast algorithm for sparse representation and further improvement of sparse representation. The following research work has been carried out on class performance. (1) a face recognition algorithm using bit plane images to represent classification voting decision is proposed. The principle of regularized least squares cooperative representation (CRC_RLS) classification algorithm is studied, and the difference and relation with the sparse representation classification (SRC) and their difference in recognition performance are analyzed. On this basis, the cooperative representation algorithm is improved by using the bit plane information and voting decision algorithm of the face image to improve the accuracy of the cooperative representation classification algorithm and the recognition speed of the sparse representation algorithm. The algorithm uses the cumulative distribution function to highlight the contour of the face image and enhance the recognition information in the image. Carry out histogram equalization. The image is decomposed by bit plane, and multiple binary bit plane images containing different types of information are obtained. The same bit plane is composed of the same plane database. In this paper, a 256 level gray image is used to experiment. One face image can decompose 8 bit plane images and a gray face image library is expanded. 8 different plane face images are developed. The correct recognition rate of each bit plane is trained by cooperative representation classification algorithm. The experiment shows that after the image is balanced, second bit planes and eighth bit planes have the same correct recognition rate, and the correct recognition rate of both third and fourth bit planes is below 0.25. 1,5,6,7,8 and other 5 bit planes, using the cooperative representation algorithm to identify the input images respectively. The 5 recognition results are voted by "the highest vote". When the majority of the voting results are not unique, it is defined as the vote decision failure, and the two decision is made: using the image to construct the virtual weighted image, in the virtual weighted image. The cooperative representation algorithm is used to classify the image again. The binary bit plane image is used instead of the two value gray level plane image to avoid the "submergence" of the low level plane in the virtual weighted face image. The weight coefficient is determined by the "number of bit numbers" and "correct recognition rate" of the bit plane. The weight difference between the different level planes is different and the weight difference of the low level plane is not too large. The correct recognition rate is 97% and 98% on the ORL and FERET face database respectively. Compared with the CRC_RLS algorithm, both the 4%. and the SRC algorithm are improved, and the bit plane decomposition of the 4% and 2%. training images is improved and the weight coefficients are trained and virtual. The construction of weighted training images is completed in the training stage, which does not affect the speed of real-time face recognition, so the recognition speed is equal to that of CRC_RLS, which is more than 10 times higher than that of the SRC algorithm. (2) a face recognition algorithm based on the cooperative representation of the nearest neighbor samples is proposed. With the number of dictionary atoms increasing, the sparse representation vector is used. The complexity of the solution increases sharply, which causes the decline of the recognition speed, and the higher the similarity between the dictionary and the test images, the higher the correct recognition rate. This paper proposes an adaptive dictionary learning algorithm based on the LCP feature, which uses the dictionary to classify the test images collaborating, not only improves the recognition speed, but also improves the recognition speed. The correct recognition rate.LCP features include the local structure (LBP) and the local micro structure (Mic) two layers. The algorithm uses the negative logarithm of the chi square coefficient to define the "x2-LBP- similarity" based on the normalized histogram of the square distance of the normalized histogram, and the '2-BRD-LBP- similarity' based on the bin- proportional histogram distance from the bin-, so as to measure the image in LB The similarity degree of P feature layer is measured by Euclidean distance (MiC- similarity) on the microscopic structural feature layer. Through a large number of experiments, the legal threshold of chi 2 -LBP- similarity and X 2-BRD-LBP- similarity, the nearest neighbor threshold and the legal threshold of MiC- similarity, the range of empirical value of near neighbor threshold are discussed in detail. Histogram features and MiC features cascade / parallel, bin- proportional histogram features and MiC features cascaded / parallel four fusion methods for error rejection recognition, error reception recognition and near neighbor samples selection three problems. Combine LBP features and Mic features to determine the similarity of the image on the LCP feature, and according to the predetermined nearest neighbor threshold self threshold. The number of redundant dictionaries proposed by this algorithm is reduced to less than 2/3 of the number of trained images, and the structure of the atomic structure is more similar to the structure of the test sample, and the correct recognition rate is improved. The redundant dictionary based on the proportional histogram adaptive construction has the occlusion image. The classification has higher robustness. On the ORL, FERET, YaleB and AR face library, this algorithm improves the correct recognition rate of the SRC RLC by about 3%, using the AR library to carry out the shawl and dark mirror occlusion experiment. The correct recognition rate can reach 85%. (3) and the sparse representation of face recognition using the Gabor near neighbor and the compressed sensing reduction is proposed. Face recognition is a typical small sample problem. The dictionary that uses face image as an atomic structure does not satisfy the condition that the number of atoms is larger than the number of features. The above two algorithms first reduce the dimension of the image to satisfy the dictionary before using the cooperative representation classification, and the problem of feature selection is still existing. If pressure is used. Contraction perception can reduce the dimension of face image, avoid the problem of feature selection and overcome the small sample problem in face recognition. This algorithm extracts the low dimension Gabor feature of face image. In the Gabor feature space, the nearest neighbor of the test sample is automatically searched by the correlation coefficient and the representation matrix is formed as the representation basis. A lot of experiments prove that the method is valid. The average correlation coefficient between the data and the training sample does not depend on the specific test sample, and gives the empirical value of the correlation coefficient threshold of the legal test data. The number of medium representation is reduced by half, and the representation base and the test image have higher structural similarity, which is more in line with the requirement of the representation matrix in the compressed sensing theory. The Gauss matrix of random distribution is used as the perceptual matrix to perceive the face image, and the high dimension face image is projected on the arbitrary low dimension observation space. Identification. The orthogonal matching tracking algorithm (OMP) and linear programming optimization algorithm are used to obtain the sparse representation vector, and the test sample is completed by class by class. Compared with the SRC algorithm, the recognition speed is increased by 5 times. The correct recognition rate is increased by 5% in the unshielded recognition. The correct recognition rate for the shawl occlusion and sunshade occlusion on the AR library is correct. Increased by nearly 1 times, reaching 83% and 73%., respectively

【學(xué)位授予單位】：山東大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41
，

本文編號(hào)：1862604