本文關(guān)鍵詞： 人臉識(shí)別 人耳識(shí)別 多模態(tài)識(shí)別 點(diǎn)云配準(zhǔn) 稀疏表示　出處：《北京科技大學(xué)》2015年博士論文　論文類型：學(xué)位論文

【摘要】：隨著信息化社會(huì)的不斷發(fā)展,信息安全成為社會(huì)關(guān)注的熱點(diǎn),基于生物特征的身份識(shí)別在社會(huì)生活中的需求越來越強(qiáng)烈。近年開展的生物特征識(shí)別研究工作已經(jīng)表明,單一模態(tài)的生物特征識(shí)別在實(shí)際應(yīng)用中的準(zhǔn)確性和魯棒性難以滿足需要,多模態(tài)識(shí)別可以融合多種生物特征體,豐富個(gè)體的鑒別信息,提高識(shí)別的準(zhǔn)確性和魯棒性。以人臉和人耳兩種生物模態(tài)進(jìn)行融合的識(shí)別具有友好性和非打擾性等特點(diǎn),成為多模態(tài)生物識(shí)別研究的熱點(diǎn)之一。 受益于三維數(shù)據(jù)采集技術(shù)的發(fā)展,生物特征識(shí)別領(lǐng)域中的相當(dāng)一部分研究延伸到使用三維信息進(jìn)行識(shí)別。相對于二維識(shí)別,三維識(shí)別對光照和姿態(tài)變化的魯棒性有所提高,但仍有受表情變化的影響明顯、三維數(shù)據(jù)存儲(chǔ)和計(jì)算開銷大等不足,另外,三維識(shí)別同樣面臨著遮擋和數(shù)據(jù)缺失的問題。在非受控識(shí)別場景中,姿態(tài)、遮擋等帶來的影響使得獲取的個(gè)體生物特征數(shù)據(jù)在多數(shù)情況下是部分的,存在不可控的變化、缺失,因此實(shí)際場景下的識(shí)別往往是利用部分?jǐn)?shù)據(jù)所進(jìn)行的識(shí)別,如何利用部分?jǐn)?shù)據(jù)來進(jìn)行身份識(shí)別是生物特征識(shí)別要解決的典型核心問題之一。 為實(shí)現(xiàn)更為魯棒的身份識(shí)別,克服單一模態(tài)識(shí)別的不足,本文通過球面變換將采集到的人臉人耳三維數(shù)據(jù)轉(zhuǎn)換為以識(shí)別對象為中心進(jìn)行表達(dá),進(jìn)而生成多模態(tài)人臉人耳球面深度圖與球面紋理圖(MARS圖)。MARS圖自然融合了人臉人耳兩種模態(tài),包含了更完整的結(jié)構(gòu)信息和紋理信息,有助于克服人臉、人耳單模態(tài)識(shí)別中姿態(tài)、遮擋、表情等問題帶來的影響。MARS圖消除了平面外旋轉(zhuǎn),能夠?qū)崿F(xiàn)無需對準(zhǔn)的識(shí)別,其二維表達(dá)形式可減少數(shù)據(jù)存儲(chǔ)開銷,降低識(shí)別過程的計(jì)算復(fù)雜度。鑒于非受控場景下中的身份識(shí)別往往是利用部分?jǐn)?shù)據(jù)所進(jìn)行的識(shí)別,因此本文重點(diǎn)研究非受控場景下基于部分?jǐn)?shù)據(jù)來進(jìn)行識(shí)別的方法。在注冊階段,通過多視角三維人臉人耳數(shù)據(jù)的融合,構(gòu)建注冊時(shí)相對更為完整的全景MARS圖原型庫來表達(dá)身份信息;在識(shí)別階段,構(gòu)建單視角MARS圖并提取單視角MARS圖的局部特征與原型庫中的全景MARS圖局部特征匹配,進(jìn)行多任務(wù)稀疏表示識(shí)別。 本文的主要研究內(nèi)容和創(chuàng)新點(diǎn)包括：第一,研究把人臉人耳三維數(shù)據(jù)由以采集設(shè)備為中心的表達(dá)轉(zhuǎn)換為以識(shí)別對象為中心進(jìn)行表達(dá)的方法,提出了MARS圖的數(shù)據(jù)表達(dá)方法,降低了存儲(chǔ)和計(jì)算開銷,有助于實(shí)現(xiàn)非受控場景下無需數(shù)據(jù)對準(zhǔn)的身份識(shí)別。第二,研究三維人臉人耳定位提取方法以及非剛性部分重合的多視角數(shù)據(jù)融合方法,提出了基于膚色檢測的純?nèi)四樔硕崛∷惴ê突贐ANICP的點(diǎn)云配準(zhǔn)方法,實(shí)現(xiàn)人臉人耳的自動(dòng)提取和非剛性人臉人耳點(diǎn)云的多視角數(shù)據(jù)配準(zhǔn)和融合。第三,針對非受控場景下基于部分?jǐn)?shù)據(jù)的身份識(shí)別問題,提出了基于MARS圖仿射SIFT特征的多任務(wù)稀疏表示識(shí)別算法(ASMSRC:Affine-Sift based Multitask Sparse Represent Classifica-tion),通過多任務(wù)稀疏表示字典的構(gòu)建和多任務(wù)最優(yōu)稀疏表示系數(shù)求解,對測試樣本的局部特征進(jìn)行重構(gòu),依據(jù)平均重構(gòu)誤差進(jìn)行分類和識(shí)別。 本文提出的基于MARS圖的人臉人耳多模態(tài)識(shí)別方法同時(shí)融合了結(jié)構(gòu)特征和紋理特征,對光線變化、姿態(tài)變化、部分遮擋和表情變化具有較強(qiáng)的魯棒性,很大程度上解決了非受控場景下基于部分?jǐn)?shù)據(jù)匹配的身份識(shí)別問題。本文的研究不僅對基于人臉人耳的身份識(shí)別,而且對更廣泛領(lǐng)域中的應(yīng)用基礎(chǔ)和理論研究都是有意義的。
[Abstract]:With the continuous development of information society, information security has become the focus of the society, based on biometric identification needs in the social life of the increasingly strong. Biometrics research work carried out in recent years have shown that the single modal biometric recognition in practical application, the accuracy and robustness of the difficult to meet the needs of multi modal identification can the integration of a variety of biological characteristics, rich individual identification information, to improve the recognition accuracy and robustness. The face and ear of two biological modal fusion recognition has the characteristics of friendly and non intrusive, becomes one of the hot research of multimodal biometrics.
Benefiting from the development of three-dimensional data acquisition technology, biometric identification technology is part of the study is extended to identify the use of three-dimensional information. Compared with two-dimensional recognition, robust 3D recognition of illumination and pose changes has increased, but there are still affected by the expression was affected obviously, lack of three-dimensional data storage and computing cost etc. in addition, 3D recognition also faces occlusion and the problem of missing data. The attitude in non controlled recognition in the scene, and the occlusion caused by making the individual biometric data obtained in most cases is part of the existence, change, uncontrollable loss, therefore the recognition scenario is often identified using part of the data, how to use the data for identification is one of the core issues of typical biometric identification to solve.
In order to achieve more robust identification, to overcome the shortcomings of single modal identification, the spherical transform 3D face data acquisition to the human ear to convert to the recognition object as the center of expression, and then generate the multimodal face and ear spherical depth map and spherical texture map (MARS map).MARS map of natural fusion of face two kinds of ear mode, contains the structure information and the texture information is more complete, helps to overcome the human face, gesture, ear recognition of single mode occlusion, bring expression and so on.MARS map to eliminate the plane rotation, to achieve recognition without the alignment, the two-dimensional expression can reduce data storage overhead. To reduce the computational complexity of the recognition process. In view of the identification of uncontrolled scenarios is often in recognition by using part of the data, so this paper focuses on the research of non controlled scenarios of data based on. The method for identification. In the registration phase, through the fusion of multi view 3D face and ear data, construct the registration relatively more complete panoramic MARS prototype library to express identity information; at the recognition stage, construction of single view MARS map and MARS map extraction panoramic local features of the local feature and the prototype of single view MARS map in matching, multi task sparse representation recognition.
The main research contents and innovations include: first, the research method of face and ear by expression of 3D data acquisition equipment for conversion to the center is to identify the object as the center of the expression of the proposed MARS map data expression method, reduce the storage and computation overhead, and identity recognition helps to realize the non controlled scene without data alignment. Second fusion localization method based on 3D face extraction method of human ear and multi view data coincide with non rigid part of the proposed facial skin detection pure ear extraction algorithm and registration method based on point cloud BANICP based on the realization of the human ear face automatic extraction and non rigid face and ear point cloud multi view data registration and fusion. In third, for the non controlled scene based on the identification problem of data in the proposed MARS map affine SIFT feature recognition based on multi task sparse representation Don't (ASMSRC:Affine-Sift based Multitask Sparse Represent algorithm, Classifica-tion) by multi task sparse dictionary construction and multi task optimal sparse representation coefficients, the local characteristics of the test samples to reconstruct, classification and identification based on the average reconstruction error.
The proposed multimodal face recognition method based on MARS graph and combines ear structure feature and texture feature of light change, attitude change, has strong robustness to occlusion and facial expression changes, largely solves the identification problem based on partial data, non controlled scene. This study not only the identity recognition based on face and ear, and the application of a broader base in the field of theory and research are meaningful.

【學(xué)位授予單位】：北京科技大學(xué)
【學(xué)位級(jí)別】：博士
【學(xué)位授予年份】：2015
【分類號(hào)】：TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 王瑜;穆志純;徐正光;駱佳佳;;基于核典型相關(guān)分析的姿態(tài)人耳、人臉多模態(tài)識(shí)別[J];北京科技大學(xué)學(xué)報(bào);2008年10期

2 孫冬梅,裘正定;生物特征識(shí)別技術(shù)綜述[J];電子學(xué)報(bào);2001年S1期

3 何國輝;甘俊英;李春芝;高建虎;;人臉與虹膜特征層融合模型的研究[J];電子學(xué)報(bào);2007年07期

4 焦李成;楊淑媛;劉芳;侯彪;;壓縮感知回顧與展望[J];電子學(xué)報(bào);2011年07期

5 路錦正;張啟衡;徐智勇;彭真明;;超完備稀疏表示的圖像超分辨率重構(gòu)方法[J];系統(tǒng)工程與電子技術(shù);2012年02期

6 李世飛;王平;沈振康;;迭代最近點(diǎn)算法研究進(jìn)展[J];信號(hào)處理;2009年10期

7 王蘊(yùn)紅,譚鐵牛;現(xiàn)代身份鑒別新技術(shù)——生物特征識(shí)別技術(shù)[J];中國基礎(chǔ)科學(xué);2000年09期

，

本文編號(hào)：1477290