本文選題：人臉識別 + 二維Gabor��； 參考：《杭州電子科技大學》2017年碩士論文

【摘要】：隨著社會的發(fā)展,人臉識別在身份認證、人機交互、視頻監(jiān)控等方面得到了廣泛應(yīng)用。人臉識別技術(shù)在各行各業(yè)中發(fā)揮著巨大的作用,但是存在著很多難題有待攻克。本文主要研究遮擋條件下的人臉識別問題,從連續(xù)性遮擋的處理能力、人臉的特征提取、遮擋和非遮擋區(qū)域的圖像分割三個方面入手,展開了一系列研究工作。本文主要貢獻和創(chuàng)新點如下:(1)針對傳統(tǒng)特征提取方法進行實驗分析,本文通過特征向量選擇實驗分析了特征向量個數(shù)對人臉識別的影響。該實驗反映了PCA算法忽略了不同樣本之間的差異性,缺乏對局部特征信息的表示。另外,通過相似度匹配實驗和人臉局部特征檢測實驗對二維Gabor函數(shù)進行分析,這兩組實驗說明了二維Gabor作為數(shù)學變換的核函數(shù),可以很好的提取人臉的局部特征信息。(2)本文基于雙屬性模型改進PCA算法,然后融合局部的二維Gabor算法,提出了新的人臉識別算法(Double Attribute Model based Gabor,DAMG),從線性子空間角度研究解決遮擋條件下的人臉識別問題。該算法基于雙屬性模型將全局特征向量和誤差特征向量融合生成雙屬性特征向量,根據(jù)二維Gabor對目標圖像進行分塊化特征提取,設(shè)計整體分類器對雙屬性特征向量和局部分塊向量進行加權(quán)分類。本文通過DAMG算法的性能分析和識別錯誤的樣本分析證明了該算法在遮擋人臉的識別過程中具有非常好的魯棒性。(3)本文提出基于CV模型的雙加權(quán)誤差分布模型,從高維圖像表示的角度研究解決遮擋條件下的人臉識別問題。首先,基于CV(Chan-Vese)模型對遮擋圖像進行分割得到不同區(qū)域下的誤差圖像。其次,提出了基于梯度方向的條件概率誤差模型,與低維度特征向量相比,條件概率誤差模型具有更多的特征信息。最后,根據(jù)遮擋區(qū)域和非遮擋區(qū)域的圖像誤差分布,分別推算出兩種誤差的分布模型,形成雙加權(quán)誤差分布模型。本文通過人臉圖像隨機遮擋、人臉五官遮擋、真實人臉遮擋這三組實驗驗證了該算法和DAMG算法在遮擋條件下進行人臉識別的有效性。
[Abstract]:With the development of society, face recognition has been widely used in identity authentication, human-computer interaction, video surveillance and so on. Face recognition technology plays a great role in various industries, but there are many problems to be solved. In this paper, face recognition under occlusion conditions is mainly studied. A series of research work is carried out from three aspects: processing ability of continuous occlusion, feature extraction of face, image segmentation of occlusion and unoccluded region. The main contributions and innovations of this paper are as follows: (1) based on the experimental analysis of traditional feature extraction methods, this paper analyzes the effect of the number of feature vectors on face recognition through feature vector selection experiments. The experiment shows that the PCA algorithm ignores the differences between different samples and lacks the representation of local feature information. In addition, the two-dimensional Gabor function is analyzed by similarity matching experiment and face local feature detection experiment. The two groups of experiments show that two-dimensional Gabor is the kernel function of mathematical transformation. This paper improves the PCA algorithm based on the two-attribute model, and then fuses the local two-dimensional Gabor algorithm. A new face recognition algorithm, double Attribute Model based Gaboran, is proposed to solve the problem of face recognition under occlusion from the perspective of linear subspace. Based on the two-attribute model, the global eigenvector and the error eigenvector are fused to generate the two-attribute eigenvector, and the target image is extracted by block feature extraction based on two-dimensional Gabor. A global classifier is designed for weighted classification of dual attribute feature vectors and local block vectors. Through the performance analysis of DAMG algorithm and the sample analysis of error recognition, it is proved that the algorithm has very good robustness in the process of shading face recognition. In this paper, we propose a double-weighted error distribution model based on CV model. Face recognition under occlusion condition is studied from the point of view of high dimensional image representation. Firstly, the occlusion images are segmented based on CVV Chan-Vese model to obtain the error images in different regions. Secondly, the conditional probability error model based on gradient direction is proposed. Compared with the low-dimensional eigenvector, the conditional probability error model has more feature information. Finally, according to the image error distribution of occlusion region and unoccluded region, the distribution models of two kinds of errors are deduced, respectively, and the double-weighted error distribution model is formed. In this paper, the experiments of random occlusion, facial facial occlusion and real face occlusion in face images demonstrate the effectiveness of the proposed algorithm and DAMG algorithm for face recognition under occlusion conditions.
【學位授予單位】：杭州電子科技大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP391.41

【參考文獻】

相關(guān)期刊論文 前10條

1 劉梓;宋曉寧;唐振民;;稀疏表示和貪婪搜索的人臉分類[J];中國圖象圖形學報;2015年01期

2 張曉松;;人臉識別技術(shù)的應(yīng)用領(lǐng)域觀察[J];數(shù)字技術(shù)與應(yīng)用;2014年04期

3 袁少鋒;王士同;;基于多元混合高斯分布的多分類人臉識別方法[J];計算機應(yīng)用研究;2013年09期

4 朱偉冬;胡劍凌;;基于馬氏距離的稀疏表示分類算法[J];計算機技術(shù)與發(fā)展;2011年11期

5 趙英男;孟凡斌;金忠;;Gabor核函數(shù)窗的設(shè)置研究[J];計算機科學;2009年01期

6 杜艷明;劉齊躍;;基于多姿態(tài)臉和小波變換的動態(tài)人臉識別[J];計算機應(yīng)用;2007年S2期

7 趙麗紅;孫宇舸;蔡玉;徐心和;;基于核主成分分析的人臉識別[J];東北大學學報;2006年08期

8 張永梅;韓焱;商細云;;一種人臉的檢測與定位方法[J];中北大學學報(自然科學版);2006年03期

9 李江;郁文賢;匡剛要;宋海娜;;紅外圖像人臉識別方法[J];國防科技大學學報;2006年02期

10 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

相關(guān)博士學位論文 前3條

1 莊連生;復雜光照條件下人臉識別關(guān)鍵算法研究[D];中國科學技術(shù)大學;2006年

2 劉直芳;人臉檢測和識別的研究[D];四川大學;2004年

3 廖頻;基于統(tǒng)一概率模型的人臉識別技術(shù)[D];中國科學院研究生院（計算技術(shù)研究所）;2003年

相關(guān)碩士學位論文 前2條

1 唐蘅;基于隱馬爾可夫模型的局部遮擋和光照人臉識別[D];電子科技大學;2012年

2 楊建功;水平集活動輪廓模型在圖像分割中的應(yīng)用研究[D];陜西師范大學;2011年

，

本文編號：1865927