本文選題：特征生成　切入點(diǎn)：特征提取　出處：《東南大學(xué)》2016年博士論文

【摘要】：人臉識別技術(shù)是模式識別和計算機(jī)視覺領(lǐng)域的一個經(jīng)久不衰的研究方向,作為一種重要的生物特征識別技術(shù),在社會公共安全、監(jiān)控、身份驗(yàn)證等日常生活中具有廣泛的應(yīng)用前景。人臉識別的直接目的在于利用人臉圖像識別和驗(yàn)證個體身份,而真實(shí)場景下的人臉識別由于外部環(huán)境的光照變化,物體遮擋,人臉姿態(tài)變化和面部表情變化等因素,具有極大的挑戰(zhàn)。典型人臉識別系統(tǒng)包括以下五個部分:人臉檢測,人臉預(yù)處理,特征生成,特征提取/特征選擇,匹配和識別。而人臉特征生成和特征提取對人臉識別的精度具有最直接的影響,因此主要關(guān)注人臉識別系統(tǒng)中的特征生成和特征提取環(huán)節(jié),研究如何從原始圖像中提取有效的面部特征及如何從高維面部特征中抽取具有鑒別能力的信息,從而提高人臉識別性能。本文分別研究了經(jīng)典的局部特征描述子,稀疏低秩表示理論和協(xié)同表示方法,并在公開人臉數(shù)據(jù)集上進(jìn)行了大量的實(shí)驗(yàn)進(jìn)行驗(yàn)證方法的有效性。本文研究的具體內(nèi)容包括:(1)針對局部三值模式這類特征描述子方法在特征生成中需要選取合適的閾值來克服不同噪聲的問題,本文給出了一種閾值自適應(yīng)的局部三值模式特征和中心對稱自適應(yīng)局部三值模式,該方法利用韋伯法則,自動根據(jù)像素的灰度值選擇與之對應(yīng)的閾值,從而解決固定閾值不能適應(yīng)像素變化的缺陷,此外中心對稱自適應(yīng)局部三值模式比自適應(yīng)局部三值模式具有更低的特征維數(shù)。在ORL和FERET人臉數(shù)據(jù)庫實(shí)驗(yàn)表明,本文提出的兩種方法的識別率均優(yōu)于傳統(tǒng)的局部特征描述子方法。(2)稀疏低秩表示要求字典是過完備的,故特征提取(維數(shù)約減)仍是重要的工作。本文首先利用低秩表示理論構(gòu)建關(guān)聯(lián)圖,給出了一種基于低秩表示理論的特征提取方法,該方法利用低秩表示理論構(gòu)建核范數(shù)圖,并在此基礎(chǔ)上刻畫樣本局部緊密度和總體離散度;其次研究利用降維后子空間內(nèi)低秩表示關(guān)系設(shè)計原空間的關(guān)聯(lián)關(guān)系,給出了一種兩步迭代低秩表示投影的特征提取方法;最后,利用稀疏表示分類策略,給出一種低秩表示分析方法直接用于特征提取,避免構(gòu)造圖嵌入學(xué)習(xí)中的關(guān)聯(lián)圖。在FERET、AR、ORL人臉庫和PolyU KFP指關(guān)節(jié)庫上的實(shí)驗(yàn)表明了上述方法的有效性。(3)利用協(xié)同表示分類識別效果好,運(yùn)算速度快的優(yōu)點(diǎn),本文給出了一種協(xié)同表示投影分析特征提取方法,有效豐富了圖嵌入學(xué)習(xí)框架。該方法基于L2范數(shù)圖構(gòu)建刻畫樣本局部精密度和總體離散度,根據(jù)Fisher鑒別分析思想建立目標(biāo)函數(shù),利用廣義特征值分解計算投影矩陣。進(jìn)一步,本文給出一種非線性核協(xié)同表示分類方法,有效增強(qiáng)了協(xié)同表示分類方法的性能。該方法利用核技巧,將原始不可分的特征空間映射到高維可分的特征空間,進(jìn)行優(yōu)化求解。在多個公開數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果表明,本文提出的方法明顯優(yōu)于經(jīng)典的方法。(4)為了識別遠(yuǎn)距離監(jiān)控系統(tǒng)低分辨率人臉圖像,將高分辨率圖片和低分辨率圖片分別看作兩組不同的變量,利用典型相關(guān)分析理論,將他們投影到同一個線性空間中,實(shí)現(xiàn)不同分辨率圖片的匹配。利用此方法,本文提出了一種基于典型相關(guān)分析的遠(yuǎn)距離低分辨率退化人臉識別方法,能有效克服分辨率不一致和分辨率低的問題。在Extended Yale B、ORL和AR人臉庫上的實(shí)驗(yàn)結(jié)果表明本文方法對低分辨率圖像具有較好的魯棒性。
[Abstract]:The technology of face recognition is an important research direction and field of pattern recognition and computer vision is not bad, as a kind of important biometric technology, monitoring in public security, and has broad application prospects such as identity authentication in daily life. The direct purpose of face recognition using face recognition and verification of identity however, face recognition in real scene due to external environment changes in illumination, object occlusion, face posture and facial expression changes and other factors, is a great challenge. The typical face recognition system includes five parts: face detection, image preprocessing, feature generation, feature extraction and feature selection, matching and recognition while facial feature generation and feature extraction for face recognition accuracy is the most direct impact, so the feature generation and feature extraction ring focus in face recognition system Day, study how to effectively extract facial features from the original image and how to extract facial features from high dimension has ability to identify information, so as to improve the performance of face recognition. This paper studies the local features of classical, low rank sparse representation theory and collaborative representation method, and the validation method of the experiments were performed in the open face data sets. The specific contents of this paper include: (1) according to the local three value pattern of this feature descriptor in the feature generation need to select the appropriate threshold to overcome different noise problems, this paper presents an adaptive threshold value of three local and central symmetry adaptive pattern local three value model, the method of using Weber's law, automatically select the corresponding threshold according to the gray value of pixels, so as to solve the fixed threshold can not adapt to the change of pixel In addition, defects, central symmetry adaptive local three value model than the adaptive local three value model has a lower dimension. In the ORL and FERET face database show that the recognition method of local feature descriptor, this paper proposes two methods were better than traditional. (2) low rank sparse overcomplete dictionary is required, so feature extraction (dimensionality reduction) is an important work. This paper use low rank representation theory to construct the graph, is presented based on low rank representation theory of feature extraction method, the method of using the low rank representation of nuclear norm graph theory construction, and based on the characterization of local sample compactness and overall dispersion; secondly Study on using low dimensional subspace in low rank representation of the original space relationship between design, gives a two step iterative low rank representation extraction method of projection features; finally, using sparse representation points Such strategies, given a low rank representation of the direct analysis method for feature extraction, avoid association graph structure graph embedding learning. In FERET, AR, ORL face database and PolyU KFP refers to the joint library. Experimental results show that this method is effective. (3) the use of collaborative representation classification and recognition effect is good, the advantages of operation fast speed, this paper presents a collaborative representation projection analysis method of feature extraction, effectively enrich the graph embedding framework. The learning method based on L2 norm maps depict local sample precision and overall dispersion, according to the Fisher identification analysis thought establish objective function, using the generalized eigenvalue decomposition of the projection matrix is computed. Further, this paper given a nonlinear kernel collaborative representation classification method, effectively enhance the performance of collaborative representation classification method. This method uses the kernel feature space mapping technique, the original can not be separated into high dimensional points. Eigen space optimization algorithm. In a number of public data sets. The experimental results show that this new method is superior to the classic. (4) in order to identify the remote monitoring system of low resolution face image, the high resolution images and low resolution images are regarded as two different groups of variables, using the theory of canonical correlation analysis. They will be projected to the same linear space, realize the matching of different resolution images. By using this method, this paper proposes a face recognition method of remote degraded low resolution based on canonical correlation analysis, can effectively overcome the inconsistent resolution and low resolution of the problem. In the Extended Yale B, ORL and AR face image databases. The experimental results show that this method is robust to the low resolution image.

【學(xué)位授予單位】：東南大學(xué)
【學(xué)位級別】：博士
【學(xué)位授予年份】：2016
【分類號】：TP391.41

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 科卞;信號細(xì)微特征提取分析技術(shù)[J];電子科技大學(xué)學(xué)報;2000年02期

2 馬少華,高峰,李敏,吳成東;神經(jīng)網(wǎng)絡(luò)分類器的特征提取和優(yōu)選[J];基礎(chǔ)自動化;2000年06期

3 管聰慧,宣國榮;多類問題中的特征提取[J];計算機(jī)工程;2002年01期

4 胡威;李建華;陳波;;入侵檢測建模過程中特征提取最優(yōu)化評估[J];計算機(jī)工程;2006年12期

5 朱玉蓮;陳松燦;趙國安;;推廣的矩陣模式特征提取方法及其在人臉識別中的應(yīng)用[J];小型微型計算機(jī)系統(tǒng);2007年04期

6 趙振勇;王保華;王力;崔磊;;人臉圖像的特征提取[J];計算機(jī)技術(shù)與發(fā)展;2007年05期

7 馮海亮;王麗;李見為;;一種新的用于人臉識別的特征提取方法[J];計算機(jī)科學(xué);2009年06期

8 朱笑榮;楊德運(yùn);;基于入侵檢測的特征提取方法[J];計算機(jī)應(yīng)用與軟件;2010年06期

9 王菲;白潔;;一種基于非線性特征提取的被動聲納目標(biāo)識別方法研究[J];軟件導(dǎo)刊;2010年05期

10 陳偉;瞿曉;葛丁飛;;主觀引導(dǎo)特征提取法在光譜識別中的應(yīng)用[J];科技通報;2011年04期

相關(guān)會議論文 前10條

1 尚修剛;蔣慰孫;;模糊特征提取新算法[A];1997中國控制與決策學(xué)術(shù)年會論文集[C];1997年

2 潘榮江;孟祥旭;楊承磊;王銳;;旋轉(zhuǎn)體的幾何特征提取方法[A];第一屆建立和諧人機(jī)環(huán)境聯(lián)合學(xué)術(shù)會議（HHME2005）論文集[C];2005年

3 薛燕;李建良;朱學(xué)芳;;人臉識別中特征提取的一種改進(jìn)方法[A];第十三屆全國圖象圖形學(xué)學(xué)術(shù)會議論文集[C];2006年

4 杜栓平;曹正良;;時間—頻率域特征提取及其應(yīng)用[A];2005年全國水聲學(xué)學(xué)術(shù)會議論文集[C];2005年

5 黃先鋒;韓傳久;陳旭;周劍軍;;運(yùn)動目標(biāo)的分割與特征提取[A];全國第二屆信號處理與應(yīng)用學(xué)術(shù)會議�？痆C];2008年

6 魏明果;;方言比較的特征提取與矩陣分析[A];2009系統(tǒng)仿真技術(shù)及其應(yīng)用學(xué)術(shù)會議論文集[C];2009年

7 林土勝;賴聲禮;;視網(wǎng)膜血管特征提取的拆支跟蹤法[A];1999年中國神經(jīng)網(wǎng)絡(luò)與信號處理學(xué)術(shù)會議論文集[C];1999年

8 秦建玲;李軍;;基于核的主成分分析的特征提取方法與樣本篩選[A];2005年中國機(jī)械工程學(xué)會年會論文集[C];2005年

9 劉紅;陳光，

本文編號：1682018