卷积神经网络的人脸隐私保护识别  

Recognition of face privacy protection using convolutional neural networks

作　　者：章坚武[1] 沈炜 吴震东[2] Zhang Jianwu;Shen Wei;Wu Zhendong(School of Communication Engineering,Hangshou Dianai Unicersity,Hangzhou 310018,China;School of Cyberspace,Hangshou Diansi University,Hangzhou 310018,China)

机构地区：[1]杭州电子科技大学通信工程学院,杭州310018 [2]杭州电子科技大学网络空间安全学院,杭州310018

出　　处：《中国图象图形学报》2019年第5期744-752,共9页Journal of Image and Graphics

基　　金：国家自然科学基金项目(61772162);国家重点研发计划项目(2016YFB0800201);浙江省自然科学基金项目(LY16F020016)~~

摘　　要：目的近年来,随着人脸识别认证技术的发展及逐渐普及,大量人脸照片存放在第三方服务器上的现象十分普遍,如何对人脸进行隐私保护这个问题变得十分突出。方法首先对人脸图像进行预处理,然后采用Arnold变换对人脸关键部位进行分块随机置乱,并将置乱结果图输入到深度卷积神经网络中。为了解决人脸照片在分块置乱时由于本身拍照角度的原因导致的分块不均等因素,在预处理时根据人眼进行特性点定位,再据此进行对齐处理,使得预处理后的照片人眼处于同一水平线。针对人脸隐私保护及加扰置乱后图像的识别,本文提出了基于分块随机加扰的深度卷积神经网络模型。不包含附加层,该模型网络结构由4个卷积层、3个池化层、1个全连接层和1个softmax回归层组成。服务器端通过深度神经网络模型直接对置乱后人脸图像进行验证识别。结果该算法使服务器端全程不存储原始人脸模板,实现了对原始人脸图像的有效加扰保护。实验采用该T深度卷积神经网络对处理过后的ORL人脸库进行识别,最终识别准确率达到97. 62%。同时通过多组对比实验,验证了本文方法的有效性。结论与其他文献中手工提取特征并利用决策树和随机森林进行训练识别的方法相比,本文方法减少了人工提取特征的工作量,且具有高识别率。Objective The development and popularization of face recognition authentication technology in recent years has made the storage of a large number of face photos in third-party servers highly common.Face recognition plays an important role in clothing,food,housing,and various industries,and moves from theoretical research to practical application of the"blowout period".However,faces are relatively open features compared to irises and fingerprints,and many people post selfies on various social platforms.Not only can you get face photos easily through the Internet,but you can also use a variety of image processing tools to fake faces.Thus,the protection of the privacy of face information has become prominent.At present,the research content in the field of face recognition focuses on directly recognizing face images,and there is a problem of privacy leakage;or the face image is encrypted and decrypted,but the encryption and decryption operation hasthe disadvantage of high computational complexity.Method To solve the problem of the unevenness of the face in a scrambled photo due to camera angles,this study preprocesses the face image as follows.First,we determine whether a given image contains a face.If a face does exist,then we find the border that contains the complete face.Next,we must locate the key points such as the nose and eyes,align the face images on the basis of these key point positions,and normalize them to the same size following the key mechanism of vision.That is,the human eye consistently sees the center of the photo first and then gradually moves to the last four corners.Then,the key parts of the face(eyes,ears,mouth,and nose)are scrambled and blocked by Arnold transform for a random number of times.Second,to achieve face privacy protection and image recognition after scrambling,this study proposes a deep convolutional neural network based on block random scrambling,which does not include an additional layer.The network structure of the model is composed of four convolutional layers,three pooling lay

关 键 词：人脸识别认证 卷积神经网络 ARNOLD变换 人脸对齐 人脸隐私保护 

分 类 号：TN911.73[电子电信—通信与信息系统] TP391.4[电子电信—信息与通信工程]