發(fā)布時(shí)間：2018-06-13 01:43

  本文選題：D卷積神經(jīng)網(wǎng)絡(luò) + 活體人臉檢測(cè)　； 參考：《信號(hào)處理》2017年11期

【摘要】：非法入侵者通過偽裝人臉騙取系統(tǒng)認(rèn)證,給人臉認(rèn)證系統(tǒng)帶來(lái)了嚴(yán)重的威脅。因此,活體人臉檢測(cè)成了人臉認(rèn)證系統(tǒng)走向?qū)嵱帽仨毥鉀Q的一個(gè)重要課題�，F(xiàn)有活體人臉檢測(cè)方法多為基于照片的人臉攻擊方面的研究成果,對(duì)于基于視頻的人臉攻擊,效果并不理想。3D卷積神經(jīng)網(wǎng)絡(luò)(Convolutional Neural Network,CNN)具有深度學(xué)習(xí)的特點(diǎn),能自動(dòng)學(xué)到圖像的分布式特征表示;與2D卷積相比,它能學(xué)到連續(xù)視頻幀的動(dòng)作信息。本文結(jié)合3D卷積神經(jīng)網(wǎng)絡(luò)的特性,提出利用3D卷積實(shí)現(xiàn)視頻人臉偽裝檢測(cè)。通過提取3D卷積神經(jīng)網(wǎng)絡(luò)最后全連接層學(xué)到的時(shí)間空間特征,訓(xùn)練SVM(Support Vector Machine)分類器,實(shí)現(xiàn)真實(shí)人臉和偽裝人臉的分類。實(shí)驗(yàn)采用兩個(gè)人臉偽裝公開數(shù)據(jù)庫(kù)Replay Attack和CASIA,實(shí)現(xiàn)多尺度內(nèi)部數(shù)據(jù)庫(kù)測(cè)試和交叉數(shù)據(jù)庫(kù)測(cè)試。實(shí)驗(yàn)結(jié)果相對(duì)于紋理特征及2D卷積方法有較大提高,可應(yīng)用于視頻人臉攻擊的活體人臉檢測(cè)。
[Abstract]:Illegal intruders deceptive system authentication by camouflage face, bring serious threat to face authentication system. Therefore, face detection in vivo has become an important issue that must be solved in the face authentication system. Most of the existing face detection methods are based on photos. For video-based face attacks, the effect is not ideal. 3D convolutional neural network (CNN) has the characteristics of deep learning. It can automatically learn the distributed feature representation of images, and it can learn the action information of continuous video frames compared with 2D convolution. Based on the characteristics of 3D convolution neural network, a video face camouflage detection based on 3D convolution is proposed in this paper. By extracting the temporal and spatial features of 3D convolutional neural network and training SVM support Vector Machine, the classification of real face and camouflage face is realized. Two human face camouflaged open databases, replay Attack and CASIA, are used to realize multi-scale internal database testing and cross-database testing. Compared with the texture features and 2D convolution, the experimental results can be applied to live face detection of video face attacks.
【作者單位】： 五邑大學(xué)信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61372193,61070167) 廣東高校優(yōu)秀青年教師培訓(xùn)計(jì)劃資助項(xiàng)目(SYQ2014001) 廣東省特色創(chuàng)新項(xiàng)目(2015KTSCX143,2015KTSCX145) 廣東省青年創(chuàng)新項(xiàng)目(2016KQNCX171)
【分類號(hào)】：TP183;TP391.41
，

本文編號(hào)：2012074