本文選題：低分辨率 + 人臉識(shí)別��； 參考：《西安理工大學(xué)》2017年碩士論文

【摘要】：人臉識(shí)別一直是人工智能和機(jī)器視覺(jué)領(lǐng)域的熱門(mén)研究方向,廣泛應(yīng)用在各個(gè)方面。對(duì)視力健全的人來(lái)說(shuō),可以很輕易地識(shí)別出一副人臉,但是要使盲人準(zhǔn)確的識(shí)別每一個(gè)熟知的人就十分困難。人臉識(shí)別系統(tǒng)是幫助盲人提升識(shí)別效果、改善生活質(zhì)量的最好選擇,因?yàn)槊娌刻卣魇侨伺c人之間最明顯的差異。本文以輔助盲人識(shí)別為大背景,并且根據(jù)盲人所處環(huán)境相對(duì)簡(jiǎn)單和盲人視覺(jué)假體項(xiàng)目,設(shè)計(jì)了適用于盲人的特定環(huán)境低分辨率人臉識(shí)別系統(tǒng),整個(gè)系統(tǒng)在FPGA平臺(tái)上進(jìn)行了驗(yàn)證。全面分析現(xiàn)有的低分辨率人臉識(shí)別算法在特定環(huán)境下的識(shí)別效果后,本文選取了識(shí)別效果最佳的主成分分析和線性鑒別分析相組合的算法,實(shí)驗(yàn)結(jié)果表明該算法在特定環(huán)境下的人臉庫(kù)中可達(dá)95%左右的識(shí)別率。依據(jù)算法原理和訓(xùn)練結(jié)果,本文完成了識(shí)別模塊的硬件電路設(shè)計(jì)。硬件電路分為三個(gè)模塊,包括特征提取模塊、歐氏距離計(jì)算模塊、最小歐氏距離提取模塊,并且在FPGA平臺(tái)上進(jìn)行驗(yàn)證和測(cè)試。結(jié)果表明,硬件識(shí)別模塊可以正確識(shí)別測(cè)試的低分辨率人臉圖像,且識(shí)別時(shí)間為20us左右,遠(yuǎn)遠(yuǎn)高于軟件識(shí)別的速度。為了更好的將硬件識(shí)別模塊應(yīng)用到輔助盲人識(shí)別的系統(tǒng)中去,本文使用SOPC技術(shù)搭建了一個(gè)系統(tǒng),并將硬件識(shí)別模塊使用Avalon總線掛載到系統(tǒng)。系統(tǒng)根據(jù)硬件識(shí)別模塊的識(shí)別結(jié)果調(diào)取SD卡中相應(yīng)的高分辨率人臉圖像并通過(guò)VGA顯示。實(shí)驗(yàn)結(jié)果表明,除去系統(tǒng)第一次啟動(dòng)時(shí)間,系統(tǒng)完成一次識(shí)別和顯示過(guò)程大約需要0.16s的時(shí)間,即系統(tǒng)幀率可達(dá)6fps。本文在全面分析現(xiàn)有的低分辨率人臉識(shí)別算法的基礎(chǔ)上,通過(guò)理論和實(shí)驗(yàn)證明主成分分析加線性鑒別分析算法在特定環(huán)境下的識(shí)別效果具有明顯優(yōu)勢(shì),對(duì)今后類似的研究有一定的參考意義。
[Abstract]:Face recognition has been a hot research direction in the field of artificial intelligence and machine vision. It is widely used in all aspects. For people with sound vision, a face can be easily identified, but it is very difficult for the blind to identify each well known person accurately. The best choice for good quality of life is that the facial features are the most obvious differences between people. This paper designs a specific environment low resolution face recognition system for blind people based on the blind person recognition and the blind human visual prosthesis. The whole system is on the FPGA platform. After analyzing the recognition effect of the existing low resolution face recognition algorithm in a specific environment, this paper selects the algorithm of combination of the principal component analysis and the linear discriminant analysis which has the best recognition effect. The experimental results show that the algorithm can reach about 95% recognition rate in the face database under a specific environment. The hardware circuit of the recognition module is completed in this paper. The hardware circuit is divided into three modules, including feature extraction module, Euclidean distance calculation module, minimum Euclidean distance extraction module, and the verification and test on the FPGA platform. The results show that the hardware recognition module can correctly identify the low resolution face of the test face. The image, and the recognition time is about 20us, is far higher than the speed of the software recognition. In order to better apply the hardware recognition module to the auxiliary blind recognition system, this paper uses the SOPC technology to build a system and mount the hardware recognition module to the system using the Avalon bus. The system is adjusted according to the recognition result of the hardware recognition module. The corresponding high resolution face images in the SD card are taken and displayed by VGA. The experimental results show that the system completes the process of recognition and display for a time of about 0.16s, that is, the system frame rate is up to 6fps., which is based on the analysis of the existing low resolution face recognition algorithm and through theory and reality. It is proved that the recognition effect of the principal component analysis and the linear discriminant analysis algorithm in the specific environment has obvious advantages, and it has some reference significance for the similar research in the future.
【學(xué)位授予單位】：西安理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TN791;TP391.41

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 張敏;張海艷;劉亭;喬夢(mèng)萱;;人臉識(shí)別系統(tǒng)綜述[J];電子世界;2014年15期

2 伊力哈木·亞爾買買提;謝麗蓉;孔軍;;基于PCA變換與小波變換的遙感圖像融合方法[J];紅外與激光工程;2014年07期

3 朱志潔;張宏偉;韓軍;宋衛(wèi)華;;基于PCA-BP神經(jīng)網(wǎng)絡(luò)的煤與瓦斯突出預(yù)測(cè)研究[J];中國(guó)安全科學(xué)學(xué)報(bào);2013年04期

4 陳昌華;譚俊;尹健康;張飛;姚進(jìn);;基于PCA-RBF神經(jīng)網(wǎng)絡(luò)的煙田土壤水分預(yù)測(cè)[J];農(nóng)業(yè)工程學(xué)報(bào);2010年08期

5 張志偉;楊帆;夏克文;楊瑞霞;;一種有監(jiān)督的LPP算法及其在人臉識(shí)別中的應(yīng)用[J];電子與信息學(xué)報(bào);2008年03期

6 李瑩輝;吳開(kāi)杰;柴新禹;任秋實(shí);;視覺(jué)假體的發(fā)展與研究[J];中國(guó)醫(yī)學(xué)物理學(xué)雜志;2007年05期

7 王衛(wèi)東;鄭宇杰;楊靜宇;楊健;;一種基于預(yù)分類的高效最近鄰分類器算法[J];計(jì)算機(jī)科學(xué);2007年02期

相關(guān)博士學(xué)位論文 前2條

1 王智飛;低分辨率人臉識(shí)別算法研究[D];北京交通大學(xué);2013年

2 山世光;人臉識(shí)別中若干關(guān)鍵問(wèn)題的研究[D];中國(guó)科學(xué)院研究生院（計(jì)算技術(shù)研究所）;2004年

相關(guān)碩士學(xué)位論文 前1條

1 羅杰俊;基于Nios II的SOPC應(yīng)用技術(shù)研究[D];哈爾濱工業(yè)大學(xué);2009年

，

本文編號(hào)：1952060