摘要
生物特征识别系统必须拥有快速准确的分类能力。针对传统人脸活体检测方法的特征提取单一和基于深度学习的检测算法中的网络训练时间长、梯度容易消失以及过拟合等问题,提出一种新型人脸活体检测算法BM-CNN(based on mixnetwork-convolutional neural network)。算法首先采用人脸分割技术和基于曲率滤波的图像增强技术对人脸图像进行预处理,然后使用优化卷积神经网络(convolutional neural network,CNN)对预处理图像进行特征提取与决策分类。对卷积神经网络,提出一种复合的并行卷积神经网络,CNN使用二均值池化策略,并综合批量归一化BN(batch normalization)方法和多类型非线性单元提高算法检测性能,通过双线并行的卷积神经网络对活体人脸进行检测。在NUAA数据库和CASIA数据库上对算法进行对比实验,实验结果显示该算法能对人脸图像进行准确的分类,并在样本数量和训练时间上有较大的提升。
Biometric identification systems should have fast and accurate classification capabilities. Aiming at the problems of traditional face detection methods, such as single feature extraction and long training time, gradient easy to disappear and over-fitting based on deep learning algorithm, a novel face detection algorithm BM-CNN(based on mixnetwork-convolutional neural network) is proposed. The algorithm firstly uses human face segmentation and image enhancement based on curvature filtering to preprocess human face image, and then uses the optimized convolutional neural network(CNN) to preprocess image feature extraction and decision classification. For the convolutional neural network, a new parallel convolutional network and a new pooling strategy are proposed. CNN uses double-mean pooling strategy and a batch normalization(BN) method and multiple types of nolinear units to improve the algorithm detection performance. BM-CNN detects the human face through the double-line convolutional neural network strategy. Finally, this paper conducts comparative experiments on NUAA and CASIA datasets. The experimental results show that the algorithm can classify the face images accurately and also has some improvement in terms of sample size and training time.
引文
[1]Blasco J,Chen T M,Tapiador J,et al.A survey of wearable biometric recognition systems[J].ACM Computing Surveys,2016,49(3):43.
[2]Peng Fei,Qin Le,Long Min.Face presentation attack detection using guided scale texture[J].Multimedia Tools and Applications,2018,77(7):8883-8909.
[3]M??tt?J,Hadid A,Pietik?inen M.Face spoofing detection from single images using texture and local shape analysis[J].IET Biometrics,2012,1(1):3-10.
[4]M??tt?J,Hadid A,Pietik?inen M.Face spoofing detection from single images using micro-texture analysis[C]//Proceedings of the International Joint Conference on Biometrics,Washington,Oct 11-13,2011.Piscataway:IEEE,2011:1-7.
[5]Li Jiangwei,Wang Yunhong,Jain A K.Live face detection based on the analysis of Fourier spectra[J].Proceedings of SPIE,2004,5404:296-303.
[6]Kim W,Suh S,Han J J.Face liveness detection from a single image via diffusion speed model[J].IEEE Transactions on Image Processing,2015,24(8):2456-2465.
[7]Pan Gang,Sun Lin,Wu Zhaohui,et al.Eyeblink-based antispoofing in face recognition from a generic webcamera[C]//Proceedings of the IEEE 11th International Conference on Computer Vision,Rio de Janeiro,Oct 14-20,2007.Washington:IEEE Computer Society,2007:1-8.
[8]Pinto A,Pedrini H,Schwartz W R,et al.Face spoofing detection through visual codebooks of spectral temporal cubes[J].IEEE Transactions on Image Processing,2015,24(12):4726-4740.
[9]Singh A K,Joshi P,Nandi G C.Face recognition with liveness detection using eye and mouth movement[C]//Proceedings of the International Conference on Signal Propagation and Computer Technology,Ajmer,Jul 12-13,2014.Piscataway:IEEE,2014:592-597.
[10]Pinto A,Schwartz W R,Pedrini H,et al.Using visual rhythms for detecting video-based facial spoof attacks[J].IEEE Transactions on Information Forensics and Security,2017,10(5):1025-1038.
[11]Yang Jianwei,Lei Zhen,Li S Z.Learn convolutional neural network for face anti-spoofing[J].arXiv:1408.5601,2014.
[12]Alotaibi A,Mahmood A.Deep face liveness detection based on nonlinear diffusion using convolution neural network[J].Signal,Image and Video Processing,2017,11(4):713-720.
[13]Alotaibi A,Mahmood A.Enhancing computer vision to detect face spoofing attack utilizing a single frame from a replay video attack using deep learning[C]//Proceedings of the International Conference on Optoelectronics and Image Processing,Warsaw,Jun 10-12,2016.Piscataway:IEEE,2016:1-5.
[14]Vincent P,Larochelle H,Bengio Y,et al.Extracting and composing robust features with denoising autoencoders[C]//Proceedings of the 25th International Conference on Machine Learning,Helsinki,Jul 5-9,2008.New York:ACM,2008:1096-1103.
[15]Ren Shaoqing,Cao Xudong,Wei Yichen,et al.Face alignment at 3000 FPS via regressing local binary features[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,Columbus,Jun 23-28,2014.Washington:IEEE Computer Society,2014:1685-1692.
[16]Yang Jianwei,Lei Zhen,Liao Shengcai,et al.Face liveness detection with component dependent descriptor[C]//Proceedings of the IEEE Conference on International Conference on Biometrics,Madrid,Jun 4-7,2013.Piscataway:IEEE,2013:1-6.
[17]Gong Yuanhao,Sbalzarini I.Curvature filters efficiently reduce certain variational energies[J].IEEE Transactions on Image Processing,2017,26(4):1786-1798.
[18]Liu W J,Liang X J.Learning performance of convolutionnal neural networks with different pooling models[J].Journal of Image and Graphics,2016,21(9):1178-1190.
[19]Ioffe S,Szegedy C.Batch normalization:accelerating deep network training by reducing internal covariate shift[C]//Proceedings of the 32nd International Conference on Machine Learning,Lille,Jul 6-11,2015:448-456.
[20]He Kaiming,Zhang Xiangyu,Ren Shaoqing,et al.Identity mappings in deep residual networks[C]//LNCS 9908:Proceedings of the 14th European Conference on Computer Vision,Amsterdam,Oct 11-14,2016.Berlin,Heidelberg:Springer,2016:630-645.
[21]Zheng Weihua,Dai Yong.Adaptive logarithm for facial illumination compensation based on homomorphic gomomorphic module[J].Journal of Image and Graphics,2011,16(8):1429-1436.
[22]Om H,Biswas M.A new image denoising scheme using soft-thresholding[J].Journal of Signal&Information Processing,2012,3(3):360-363.
[23]Zhang Zhiwei,Yan Junjie,Liu Sifei,et al.A face antispoofing database with diverse attacks[C]//Proceedings of the 5th IAPR International Conference on Biometrics,New Delhi,Mar 29-Apr 1,2012.Piscataway:IEEE,2012:26-31.
[24]Parveen S,Ahmad S M S,Abbas N H,et al.Face liveness detection using dynamic local ternary pattern(DLTP)[J].Computers,2016,5(2):10.
[25]Yu Changyong,Jia Yunde.Anisotropic diffusion-based kernel matrix model for face liveness detection[J].arXiv:1707.02692,2017.
[26]Xu Zhenqi,Li Shan,Deng Weihong.Learning temporal features using LSTM-CNN architecture for face anti-spoofing[C]//Proceedings of the 3rd IAPR Asian Conference on Pattern Recognition,Kuala Lumpur,Nov 3-6,2015.Piscataway:IEEE,2015:141-145.
[27]Atoum Y,Liu Yaojie,Jourabloo A,et al.Face anti-spoofing using patch and depth-based CNNs[C]//Proceedings of the IEEE International Joint Conference on Biometrics,Denver,Oct 1-4,2017.Piscataway:IEEE,2017:319-328.
[28]Lakshminarayana N N,Narayan N,Napp N,et al.A discriminative spatio-temporal mapping of face for liveness detection[C]//Proceedings of the IEEE International Conference on Identity,Security and Behavior Analysis,New Delhi,Feb 22-24,2017.Piscataway:IEEE,2017:1-7.
[29]Li Yuming,Po L M,Xu Xuyuan,et al.Face liveness detection and recognition using shearlet based feature descriptors[C]//Proceedings of the IEEE International Conference on Acoustics,Speech and Signal Processing,Shanghai,Mar20-25,2016.Piscataway:IEEE,2016:874-877.
[21]郑伟华,戴永.自适应同态对数光照补偿[J].中国图象图形学报,2011,16(8):1429-1436.