【摘要】：隨著大數(shù)據(jù)時(shí)代的到來,個(gè)人與國家的信息安全正在逐漸成為一個(gè)研究熱點(diǎn)。而生物識別技術(shù)因?yàn)槠浒踩�、保密性及方便性等�?yōu)點(diǎn)迅速成為了科研人員的“寵兒”。在眾多的生物特征識別技術(shù)中,人臉識別技術(shù)以其無接觸性、高效性、便捷性、唯一性、精準(zhǔn)性等優(yōu)點(diǎn)脫穎而出,發(fā)展成了研究熱度最高的生物特征識別技術(shù)。通常的人臉識別系統(tǒng)中面部特征配準(zhǔn)模塊和特征提取與比對識別模塊占有重要地位,本文針對這兩個(gè)內(nèi)容展開了深入研究,主要研究工作如下:首先,概述人臉識別的研究歷史現(xiàn)狀與基本技術(shù)方法;面部特征配準(zhǔn)的研究歷史現(xiàn)狀與技術(shù)方法;人臉比對的研究現(xiàn)狀、應(yīng)用與發(fā)展方向。接著,研究人臉檢測與人臉圖像預(yù)處理環(huán)節(jié)。對當(dāng)前存在的主要人臉檢測方法進(jìn)行了概述和分類。從特征的選擇,強(qiáng)分類器的生成,級聯(lián)檢測器的構(gòu)成詳細(xì)討論基于Haar_like特征與基于LBP特征的AdaBoost的人臉檢測方法。通過對這兩種方法的實(shí)時(shí)性與準(zhǔn)確性的比較得出基于Haar_like特征的AdaBoost人臉檢測方法具有較好的描述能力;基于LBP特征的AdaBoost人臉檢測方法時(shí)效性比較好。在檢測過后,通過尺度歸—化和灰度變換統(tǒng)一人臉區(qū)域尺寸,消除顏色信息。然后,從兩個(gè)方面對人臉面部特征配準(zhǔn)方法進(jìn)行了研究。一方面是基于幾何特征,從人臉面部特征點(diǎn)出發(fā),介紹了基于顯式形狀回歸的面部特征配準(zhǔn)方法。在不同的數(shù)據(jù)庫進(jìn)行配準(zhǔn)實(shí)驗(yàn),給出了比較全面的人臉配準(zhǔn)效果圖。另一方面是基于統(tǒng)計(jì)特征,研究基于不變形變換主成分分析的人臉配準(zhǔn)方法,討論了KL變換、特征空間的創(chuàng)建以及反向合成算法的迭代過程,用手動(dòng)對齊的標(biāo)準(zhǔn)人臉庫對該方法進(jìn)行了實(shí)驗(yàn)驗(yàn)證,結(jié)果表明,該方法能比較好地配準(zhǔn)人臉,并與識別有著相互促進(jìn)的效果。接著,研究了相似度度量問題。通常的度量方法僅僅是考慮下了一對樣本的差異性,為了增加判別性,同時(shí)考慮人臉樣本的共性和個(gè)性,采用聯(lián)合共性和個(gè)性的度量方法對人臉樣本對進(jìn)行相似度度量。并在不同數(shù)據(jù)庫對該方法進(jìn)行實(shí)驗(yàn)驗(yàn)證,結(jié)果表明該方法能去的滿意的結(jié)果。最終將所以環(huán)節(jié)聯(lián)系起來,構(gòu)建一個(gè)人臉比對系統(tǒng)。
[Abstract]:With the arrival of big data era, the information security of individuals and countries is becoming a research hotspot. Because of its advantages of safety, confidentiality and convenience, biometric technology has quickly become the favorite of researchers. Among the many biometric recognition technologies, face recognition technology has become the most popular biometric recognition technology because of its advantages of non-contact, high efficiency, convenience, uniqueness, accuracy and so on. In the common face recognition system, the facial feature registration module and the feature extraction and comparison recognition module play an important role. In this paper, the two contents of the in-depth research, the main research work is as follows: first, This paper summarizes the history and basic technical methods of face recognition, the history and technical methods of facial feature registration, and the research status, application and development direction of face matching. Then, face detection and face image preprocessing are studied. The existing methods of face detection are summarized and classified. A face detection method based on Haar_like features and AdaBoost based on LBP features is discussed in detail from feature selection, generation of strong classifiers and construction of cascaded detectors. By comparing the real-time and accuracy of the two methods, it is concluded that the AdaBoost face detection method based on Haar_like features has better description ability, and the AdaBoost face detection method based on LBP features has better timeliness. After the detection, the face region size is unified by scale normalization and gray scale transformation, and the color information is eliminated. Then, face feature registration method is studied from two aspects. On the one hand, based on geometric features and facial feature points, a facial feature registration method based on explicit shape regression is introduced. In different database registration experiments, a more comprehensive face registration effect map is given. On the other hand, based on the statistical features, the face registration method based on the principal component analysis of the invariant transformation is studied, and the KL transform, the creation of the feature space and the iterative process of the inverse synthesis algorithm are discussed. The experimental results show that the proposed method can be used to match human faces well, and it is mutually beneficial to recognition. Then, the similarity measurement problem is studied. In order to increase the discriminability and to consider the commonness and individuality of face samples, the common measurement method is used to measure the similarity of face samples. The experimental results in different databases show that the method can get satisfactory results. Finally, the link will be linked to build a human face comparison system.
【學(xué)位授予單位】：哈爾濱工程大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2016
【分類號】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前6條

1 阮曉虎;李衛(wèi)軍;覃鴻;董肖莉;張麗萍;;一種基于特征匹配的人臉配準(zhǔn)判斷方法[J];智能系統(tǒng)學(xué)報(bào);2015年01期

2 江偉堅(jiān);郭躬德;賴智銘;;基于新Haar-like特征的Adaboost人臉檢測算法[J];山東大學(xué)學(xué)報(bào)(工學(xué)版);2014年02期

3 王振奇;;人臉識別技術(shù)在安防行業(yè)的飛躍與突破——訪漢王科技股份有限公司大客戶事業(yè)部副總經(jīng)理石踐[J];中國安防;2010年08期

4 武京偉;黃春慶;;一種基于改進(jìn)彈性束圖匹配的人臉識別[J];工業(yè)控制計(jì)算機(jī);2009年09期

5 李麗娟;石紅偉;王愛云;;一種基于貝葉斯切線模型的人臉對齊算法[J];計(jì)算機(jī)工程;2009年14期

6 山世光,高文,唱軼鉦,曹波,陳熙霖;人臉識別中的“誤配準(zhǔn)災(zāi)難”問題研究[J];計(jì)算機(jī)學(xué)報(bào);2005年05期

相關(guān)碩士學(xué)位論文 前6條

1 郭志芳;基于支持向量回歸的面部特征點(diǎn)定位算法[D];南昌航空大學(xué);2015年

2 靳一凡;基于級聯(lián)卷積神經(jīng)網(wǎng)絡(luò)的人臉關(guān)鍵點(diǎn)檢測算法[D];浙江大學(xué);2015年

3 江偉;人臉面部特征點(diǎn)檢測及其在視頻監(jiān)控中的應(yīng)用[D];上海大學(xué);2015年

4 蔡超;基于面部基準(zhǔn)點(diǎn)對齊的人臉識別方法研究[D];華中科技大學(xué);2013年

5 孟繁特;人臉識別關(guān)鍵技術(shù)研究[D];哈爾濱工程大學(xué);2012年

6 吳證;人臉特征點(diǎn)定位研究及應(yīng)用[D];上海交通大學(xué);2007年

，

本文編號：2157690