人臉識(shí)別系統(tǒng)的研究與開(kāi)發(fā)
發(fā)布時(shí)間：2018-07-13 11:10
【摘要】：人臉識(shí)別技術(shù)是一種基于人臉面部特征進(jìn)行身份識(shí)別的生物特征識(shí)別技術(shù),通過(guò)使用攝像頭等采集設(shè)備提取人臉面部特征,并對(duì)其特征進(jìn)行匹配進(jìn)而實(shí)現(xiàn)身份驗(yàn)證識(shí)別。首先,本文介紹了人臉識(shí)別技術(shù)的產(chǎn)生背景、發(fā)展的歷史、優(yōu)勢(shì)、研究難點(diǎn)以及應(yīng)用領(lǐng)域,概括總結(jié)了人臉識(shí)別領(lǐng)域里的一些經(jīng)典算法并介紹了當(dāng)前國(guó)內(nèi)外科研機(jī)構(gòu)及公司在人臉識(shí)別領(lǐng)域中的重要突破。其次,本文給出了人臉識(shí)別的系統(tǒng)構(gòu)成,并深入研究了各部分所涉及的算法,之后著重分析了人臉特征提取算法對(duì)人臉識(shí)別性能的影響。人臉識(shí)別系統(tǒng)由圖像預(yù)處理、人臉檢測(cè)、人臉對(duì)齊、特征提取及特征匹配五部分構(gòu)成。圖像預(yù)處理部分是通過(guò)灰度變換以及直方圖均衡化加強(qiáng)圖像對(duì)比度;人臉檢測(cè)部分采用Viola-Jones人臉檢測(cè)算法,通過(guò)對(duì)基于Harr-like特征的訓(xùn)練集進(jìn)行訓(xùn)練得到Adaboost強(qiáng)分類器進(jìn)行人臉?lè)诸?并通過(guò)級(jí)聯(lián)分類器結(jié)構(gòu)提高檢測(cè)的速度;人臉對(duì)齊部分依據(jù)雙眼坐標(biāo)進(jìn)行平面幾何變換實(shí)現(xiàn)人臉的標(biāo)準(zhǔn)化;特征提取部分深入研究了局部二值模式算法(LBP)和局部相位量化算法(LPQ),其中LBP提取的是局部區(qū)域像素差異信息,計(jì)算簡(jiǎn)便高效,而LPQ提取的是局部相位信息,對(duì)于模糊圖像有著很強(qiáng)的魯棒性;特征匹配部分使用卡方距離計(jì)算LBP、LPQ算法提取的樣本空間距離,并研究了接收閾值的設(shè)置原理。通過(guò)對(duì)LBP、LPQ算法的仿真分析,評(píng)估這兩種算法的差異以及在不同的人臉數(shù)據(jù)庫(kù)平臺(tái)下不同條件的識(shí)別率。最后,本文人臉識(shí)別系統(tǒng)的實(shí)現(xiàn)是基于Qt可視化開(kāi)發(fā)平臺(tái),調(diào)用計(jì)算機(jī)視覺(jué)庫(kù)Open CV中相關(guān)函數(shù)模塊,尤其是人臉檢測(cè)模塊,方便快捷的實(shí)現(xiàn)系統(tǒng)的開(kāi)發(fā)工作。文中同時(shí)也給出了Qt、Open CV的相關(guān)環(huán)境參數(shù)設(shè)置及編譯方法、系統(tǒng)用戶界面、功能模塊以及系統(tǒng)最終的輸出結(jié)果。
[Abstract]:Face recognition technology is a biometric recognition technology based on facial features. Face features are extracted by using camera and other acquisition devices, and their features are matched to achieve identity identification. First of all, this paper introduces the background, development history, advantages, research difficulties and application fields of face recognition technology. This paper summarizes some classical algorithms in the field of face recognition and introduces some important breakthroughs in the field of face recognition made by domestic and foreign scientific research institutions and companies. Secondly, this paper gives the system structure of face recognition, and deeply studies the algorithms involved in each part, and then analyzes the influence of face feature extraction algorithm on the performance of face recognition. Face recognition system consists of five parts: image preprocessing, face detection, face alignment, feature extraction and feature matching. In the image preprocessing part, image contrast is enhanced by gray level transformation and histogram equalization. In the face detection part, the Adaboost strong classifier is obtained by training the Harr-like training set by using Viola-Jones face detection algorithm. The speed of detection is improved by cascaded classifier structure, and face alignment is realized by plane geometry transformation according to binocular coordinates. In the feature extraction part, the local binary mode algorithm (LBP) and the local phase quantization algorithm (LPQ) are studied in depth. The local pixel difference information extracted by LBP is simple and efficient, while the local phase information is extracted by LPQ. In the feature matching part, chi-square distance is used to calculate the sample space distance extracted by LBPU LPQ algorithm, and the principle of setting reception threshold is studied. The difference between the two algorithms and the recognition rate of different conditions under different face database platforms are evaluated by the simulation analysis of LBP- LPQ algorithm. Finally, the realization of the face recognition system is based on the QT visual development platform, which calls the correlation function module in the computer vision library Open CV, especially the face detection module, and realizes the development of the system conveniently and quickly. At the same time, the environment parameter setting and compiling method, the user interface, the function module and the final output result of QtnOpen CV are also given in this paper.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41
本文編號(hào)：2119154
[Abstract]:Face recognition technology is a biometric recognition technology based on facial features. Face features are extracted by using camera and other acquisition devices, and their features are matched to achieve identity identification. First of all, this paper introduces the background, development history, advantages, research difficulties and application fields of face recognition technology. This paper summarizes some classical algorithms in the field of face recognition and introduces some important breakthroughs in the field of face recognition made by domestic and foreign scientific research institutions and companies. Secondly, this paper gives the system structure of face recognition, and deeply studies the algorithms involved in each part, and then analyzes the influence of face feature extraction algorithm on the performance of face recognition. Face recognition system consists of five parts: image preprocessing, face detection, face alignment, feature extraction and feature matching. In the image preprocessing part, image contrast is enhanced by gray level transformation and histogram equalization. In the face detection part, the Adaboost strong classifier is obtained by training the Harr-like training set by using Viola-Jones face detection algorithm. The speed of detection is improved by cascaded classifier structure, and face alignment is realized by plane geometry transformation according to binocular coordinates. In the feature extraction part, the local binary mode algorithm (LBP) and the local phase quantization algorithm (LPQ) are studied in depth. The local pixel difference information extracted by LBP is simple and efficient, while the local phase information is extracted by LPQ. In the feature matching part, chi-square distance is used to calculate the sample space distance extracted by LBPU LPQ algorithm, and the principle of setting reception threshold is studied. The difference between the two algorithms and the recognition rate of different conditions under different face database platforms are evaluated by the simulation analysis of LBP- LPQ algorithm. Finally, the realization of the face recognition system is based on the QT visual development platform, which calls the correlation function module in the computer vision library Open CV, especially the face detection module, and realizes the development of the system conveniently and quickly. At the same time, the environment parameter setting and compiling method, the user interface, the function module and the final output result of QtnOpen CV are also given in this paper.
【學(xué)位授予單位】：吉林大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2016
【分類號(hào)】：TP391.41
【參考文獻(xiàn)】
相關(guān)期刊論文 前2條
1 甘玲;朱江;苗東;;擴(kuò)展Haar特征檢測(cè)人眼的方法[J];電子科技大學(xué)學(xué)報(bào);2010年02期
2 肖冰,王映輝;人臉識(shí)別研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2005年08期
相關(guān)碩士學(xué)位論文 前3條
1 卜秋月;基于OpenCV的人臉識(shí)別系統(tǒng)的設(shè)計(jì)與實(shí)現(xiàn)[D];吉林大學(xué);2015年
2 孫志;基于OpenCV的人臉識(shí)別算法實(shí)驗(yàn)平臺(tái)研究與實(shí)現(xiàn)[D];吉林大學(xué);2014年
3 王英明;基于AdaBoost算法的人臉檢測(cè)研究[D];南京理工大學(xué);2008年
，本文編號(hào)：2119154
本文鏈接：http://sikaile.net/kejilunwen/ruanjiangongchenglunwen/2119154.html
最近更新
教材專著
