本文選題：人臉識(shí)別 + 人臉驗(yàn)證　； 參考：《湘潭大學(xué)》2017年碩士論文

【摘要】：人臉驗(yàn)證是人臉識(shí)別研究問題中一個(gè)重點(diǎn)也是一個(gè)難點(diǎn),因?yàn)樽罱鼛啄暌蛱鼐W(wǎng)技術(shù)的發(fā)展,如何快速的進(jìn)行身份驗(yàn)證以確保個(gè)人信息安全,已經(jīng)成為一個(gè)熱門話題。由于人臉驗(yàn)證問題是身份驗(yàn)證中比較重要的生物驗(yàn)證方法,從而使人臉驗(yàn)證成為了一個(gè)新的研究熱點(diǎn)。人臉驗(yàn)證是一個(gè)二類驗(yàn)證問題即給定一張人臉圖片把它和已知身份的人臉圖片進(jìn)行對(duì)比并判斷兩張圖片是否是同一個(gè)人。本文主要是基于卷積神經(jīng)網(wǎng)絡(luò)研究的延展。在應(yīng)對(duì)于人臉驗(yàn)證問題時(shí)分成了限制性條件和非限制條件下兩種情形并且提出了兩種基于卷積神經(jīng)網(wǎng)絡(luò)的人臉驗(yàn)證模型。主要的研究工作如下:1在基于Yale B數(shù)據(jù)庫和AR數(shù)據(jù)庫兩個(gè)人臉數(shù)據(jù)庫上構(gòu)造了一個(gè)混合模型的卷積神經(jīng)網(wǎng)絡(luò)的人臉驗(yàn)證方法。相比于以前人臉驗(yàn)證方法,這種方法對(duì)人臉驗(yàn)證操作進(jìn)行了分段操作。并且使用了PCA降維和SVM的驗(yàn)證分類操作。該方法相比于傳統(tǒng)方法,在限制性實(shí)驗(yàn)環(huán)境下人臉驗(yàn)證的準(zhǔn)確率有較好的提升。2在應(yīng)對(duì)非限制條件下人臉圖片時(shí)由于混合卷積神經(jīng)網(wǎng)絡(luò)的局限性,所以對(duì)上述的混合卷積神經(jīng)網(wǎng)絡(luò)進(jìn)行了優(yōu)化和改進(jìn)從而構(gòu)造了一個(gè)并行三通道卷積神經(jīng)網(wǎng)絡(luò)結(jié)構(gòu)的人臉驗(yàn)證模型。3在LFW數(shù)據(jù)庫上構(gòu)造了兩種不同的連接方式的三通道并行卷積神經(jīng)網(wǎng)絡(luò)模型。第一種采用了傳統(tǒng)的全連接的方式。第二種是使用了局部連接的方式。使用兩種連接的網(wǎng)絡(luò)是為了比較在不同的連接方式下那種連接方式可以提高準(zhǔn)確率。為了提高整個(gè)模型的正確率,模型進(jìn)行了兩次訓(xùn)練。第一次使用了SGD的優(yōu)化函數(shù)進(jìn)行首次訓(xùn)練,并保存下最好結(jié)果的模型。第二次使用了Adadelta優(yōu)化函數(shù)在第一次訓(xùn)練好的模型上進(jìn)行了二次訓(xùn)練以此來提高整個(gè)模型的準(zhǔn)確率。
[Abstract]:Face verification is an important and difficult problem in face recognition, because with the development of Internet technology in recent years, how to quickly authenticate to ensure the security of personal information has become a hot topic.Face verification is an important biometric method in authentication, which makes human face verification become a new research hotspot.Face verification is a kind of verification problem that is to compare a face image with a face image of known identity and judge whether two images are the same person.This paper is mainly based on the extension of convolution neural network research.In this paper, the face verification problem is divided into two cases: restricted and unconstrained, and two kinds of face verification models based on convolution neural network are proposed.The main work of this paper is as follows: 1. Based on Yale B database and AR database, we construct a hybrid model based on convolution neural network for face verification.Compared with the previous face verification method, this method performs segmentation operation.And the verification classification operation of PCA reduction and SVM is used.Compared with the traditional method, the accuracy of face verification in the restricted experimental environment is better than that of the traditional one. 2. When dealing with face images under unconstrained conditions, the proposed method is limited by hybrid convolution neural networks.So the hybrid convolution neural network mentioned above is optimized and improved to construct a parallel three-channel convolutional neural network model of face verification. 3. 3 constructs two kinds of three different connection modes on LFW database.Channel parallel convolution neural network model.The first uses the traditional full-connected approach.The second is the use of local connections.Two kinds of connection networks are used to compare which connection modes can improve the accuracy of different connection modes.In order to improve the accuracy of the whole model, the model was trained twice.For the first time, the optimization function of SGD is used for the first time, and the best result model is saved.In the second time, the Adadelta optimization function is used to improve the accuracy of the model.
【學(xué)位授予單位】：湘潭大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TP183

【參考文獻(xiàn)】

相關(guān)期刊論文 前2條

1 曹林;周汐;;結(jié)合SIFT特征的人臉驗(yàn)證[J];計(jì)算機(jī)工程與應(yīng)用;2016年08期

2 朱建新,楊小虎,董金祥,曹哲新;生物認(rèn)證系統(tǒng)設(shè)計(jì)研究[J];計(jì)算機(jī)工程與應(yīng)用;2002年10期

相關(guān)博士學(xué)位論文 前1條

1 山世光;人臉識(shí)別中若干關(guān)鍵問題的研究[D];中國科學(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 葉浪;基于卷積神經(jīng)網(wǎng)絡(luò)的人臉識(shí)別研究[D];東南大學(xué);2015年

，

本文編號(hào)：1750425