[1]张媛媛,霍静,杨婉琪,等.深度信念网络的二代身份证异构人脸核实算法[J].智能系统学报,2015,10(2):193-200.[doi:10.3969/j.issn.1673-4785.201405060]
ZHANG Yuanyuan,HUO Jing,YANG Wanqi,et al.A deep belief network-based heterogeneous face verification method for the second-generation identity card[J].CAAI Transactions on Intelligent Systems,2015,10(2):193-200.[doi:10.3969/j.issn.1673-4785.201405060]
点击复制
ZHANG Yuanyuan,HUO Jing,YANG Wanqi,et al.A deep belief network-based heterogeneous face verification method for the second-generation identity card[J].CAAI Transactions on Intelligent Systems,2015,10(2):193-200.[doi:10.3969/j.issn.1673-4785.201405060]
深度信念网络的二代身份证异构人脸核实算法
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
10
期数:
2015年第2期
页码:
193-200
栏目:
学术论文—机器感知与模式识别
出版日期:
2015-04-25
- Title:
- A deep belief network-based heterogeneous face verification method for the second-generation identity card
- Keywords:
- face recognition; multimodes; deep learning; deep belief network
- 分类号:
- TP391
- 文献标志码:
- A
- 摘要:
- 二代身份证人脸核实问题是指判断二代身份证人像和身份证使用者当前头像是否为同一人。具体来说,即将二代身份证模糊人像和实际在光照、背景等因素不可控环境下拍摄的若干张二代证使用者的视频人像作匹配,判断是否为同一个人。由于低分辨率模糊图像和清晰视频图像属于2种不同的图像模态,因此该问题属于异构人脸识别问题。考虑到跨模态人脸图像的差异,传统的特征抽取方法很难抽取判别性特征来描述不同模态图像,使得传统方法难以达到精准辨别。针对这个问题,提出了一种新的基于深度学习的解决方法,其基本思想是通过深度信念网络(DBN)的非监督贪心逐层训练来提取人脸图像的高层特征,结合传统的图像预处理和相似性度量技术,达到人脸核实的目的。通过在256人的真实二代证数据集上和传统特征降维方法PCA、LDA进行比较,证实了所提出方法在准确率上相比PCA有约12%的提升,相比LDA有约8%的提升。实验同时表明,针对数据量增大的情况,基于深度学习的解决方法要优于传统的人脸识别方法。
- Abstract:
- The objective of the face verification method for the second-generation identity card is to determine whether the original head-photo stored in the corresponding identity card image and the currently captured head photo of the card-holder by using a video camera image actually belongs to the same person or not. To obtain a good verification result for the heterogeneous face verification method is a very challenging task because the two different types of images belong to two different modalities (e.g., different image resolutions, different illumination conditions). Considering the difference of trans-modal face images, it is hard to use traditional feature extraction methods to extract discriminative feature for description of images with different modes. Traditional feature extraction methods cannot distinguish images exactly. In this paper, a deep learning-based face verification method is proposed. The proposed deep learning-based face verification method integrates the deep belief network (DBN), which employs unsupervised greedy layer-by-layer training for high-level feature extraction of face photo and combines the popularly used image preprocessing and similarity measurement technologies to realize the purpose of face verification. The results were evaluated on a real dataset with two different modalities of 256 different people. This method outperforms the traditional principal component analysis (PCA) and linear discriminant analysis (LDA) methods with 12% and 8% improvements in terms of the verification accuracy, respectively. The results validated the advantage of the proposed method, especially when the amount of entries increases.
- 参考文献/References:
-
[1] CHAN C H, TAHIR M A, KITTLER J, et al. Multiscale local phase quantization for robust component-based face recognition using kernel fusion of multiple descriptors[J]. Pattern Analysis and Machine Intelligence, 2013, 35(5): 1164-1177.
[2] LIAO S, JAIN A K, LI S Z, et al. Partial face recognition: alignment-free approach[J]. Pattern Analysis and Machine Intelligence, 2013, 35(5): 1193-1205.
[3] CAO X, WIPF D, WEN F, et al. A practical transfer learning algorithm for face verification[C]//The IEEE International Conference on Computer Vision. Sydney, Australia, 2013: 3208-3215.
[4] SIROVICH L, KIRBY M. Low-dimensional procedure for the characterization of human faces[J]. Journal of the Optical Society of America, 1987, 4(3): 519-524.
[5] TURK M A, PENTLAND A P. Face recognition using eigenfaces[C]//Computer Vision and Pattern Recognition.[S.l.], 1991: 586-591.
[6] SCHOLKOPFT B, MULLERT K R. Fisher discriminant analysis with kernels[C]//Proc of IEEE International Workshop on Neural Networks for Signal Processing. Madison, USA, 1999: 41-48.
[7] HE X, NIYOGI P. Locality preserving projections[C]//Annual Conference on Neural Information Processing Systems. British Columbia, Canada, 2003, 16: 234-241.
[8] BENGIO Y, LAMBLIN P, POPOVICI D, et al. Greedy layer-wise training of deep networks[C]//Neural Information Processing Systems. Vancouver, Canada, 2007, 19: 153-160.
[9] LIN D, TANG X. Inter-modality face recognition[J]. European Conference on Computer Vision, 2006, 3954(4): 13-26.
[10] HINTON G E, OSINDERO S, TEH Y W, et al. A fast learning algorithm for deep belief nets[J]. Neural Computation, 2006, 18(7): 1527-1554.
[11] HINTON G E. Learning multiple layers of representation[J]. Trends in Cognitive Sciences, 2007, 11(10): 428-434.
[12] BARKAN O, WEILL J, WOLF L, et al. Fast high dimensional vector multiplication face recognition[C]//The IEEE International Conference on Computer Vision. Sydney, Australia, 2013: 1-8.
[13] SIMONYAN K, PARKHI O M, VEDALDI A, et al. Fisher vector faces in the wild[C]//Proc British Machine Vision Conference. Bristol, UK, 2013: 1-12.
[14] CUI Z, LI W, XU D, et al. Fusing robust face region descriptors via multiple metric learning for face recognition in the wild[C]//Computer Vision and Pattern Recognition. Portland, Oregon, 2013: 3554-3561.
[15] KLARE B, JAIN A K. Heterogeneous face recognition: matching NIR to visible light images[C]//International Conference on Pattern Recognition. Istanbul, Turkey, 2010: 1513-1516.
[16] YI D, LIU R, CHU R, et al. Face matching between near infrared and visible light images[J]. Advances in Biometrics, 2007, 4642: 523-530.
[17] WANG R, YANG J, YI D, et al. An analysis-by-synthesis method for heterogeneous face biometrics[J]. Advances in Biometrics, 2009, 5558: 319-326.
[18] CHEN J, YI D, YANG J, et al. Learning mappings for face synthesis from near infrared to visual light images[C]//Computer Vision and Pattern Recognition. Fla, USA, 2009: 156-163.
[19] SUN Y, WANG X, TANG X, et al. Hybrid deep learning for face verification[C]//IEEE International Conference on Computer Vision. Sydney, Australia, 2013: 1489-1496.
[20] HUANG G B, RAMESH M, BERG T, et al. Labeled faces in the wild: a database for studying face recognition in unconstrained environments[R]. Massachusetts, Amherst, 2007: 07-49.
[21] HINTON G. A practical guide to training restricted Boltzmann machines[J]. Momentum, 2010, 9(1): 599-619.
[22] HINTON G.Training products of experts by minimizing contrastive divergence[J]. Neural Computation, 2002,14(8): 1771-1800.
[23] HINTON G. Learning multiple layers of representation[J]. Trends in Cognitive Sciences, 2007, 11(10): 428-434.
[24] HINTON G. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.
[25] EDWARDS G J, COOTES T F, TAYLOR C J, et al. Face recognition using active appearance models[J]. Computer Vision—(ECCV). 1998,1407: 581-595.
[26] VIOLA P, JONES M. Fast and robust classification using asymmetric adaboost and a detector cascade[C]//Neural Information Processing Systems. Vancouver, Canada, 2002: 1311-1318.
[27] 余凯, 贾磊, 陈雨强, 等. 深度学习的昨天, 今天和明天[J]. 计算机研究与发展[J], 2013,50(9): 1799-1804.YU Kai, JIA Lei, CHEN Yuqiang, et al. Yesterday, today and tomorrow for deep learning[J]. Journal of Computer Research and Development, 2013, 50(9): 1799-1804.
[28] HUANG G B, LEE H, LEARNED-MILLER E, et al. Learning hierarchical representations for face verification with convolutional deep belief networks[C]//Computer Vision and Pattern Recognition. Newport, USA, 2012: 2518-2525.
- 相似文献/References:
-
[1]李雪,蒋树强.智能交互的物体识别增量学习技术综述[J].智能系统学报,2017,12(2):140.[doi:10.11992/tis.201701006]
LI Xue,JIANG Shuqiang.Incremental learning and object recognition system based on intelligent HCI: a survey[J].CAAI Transactions on Intelligent Systems,2017,12():140.[doi:10.11992/tis.201701006]
[2]吴钟强,张耀文,商琳.基于语义特征的多视图情感分类方法[J].智能系统学报,2017,12(5):745.[doi:10.11992/tis.201706026]
WU Zhongqiang,ZHANG Yaowen,SHANG Lin.Multi-view sentiment classification of microblogs based on semantic features[J].CAAI Transactions on Intelligent Systems,2017,12():745.[doi:10.11992/tis.201706026]
[3]侯涛,张强.基于T-S型模糊加权的多模软切换的风电机组变桨控制[J].智能系统学报,2018,13(4):625.[doi:10.11992/tis.201710009]
HOU Tao,ZHANG Qiang.Multi-mode soft-switch variable-pitch control of wind turbines based on T-S fuzzy weighting[J].CAAI Transactions on Intelligent Systems,2018,13():625.[doi:10.11992/tis.201710009]
[4]张新钰,邹镇洪,李志伟,等.面向自动驾驶目标检测的深度多模态融合技术[J].智能系统学报,2020,15(4):758.[doi:10.11992/tis.202002010]
ZHANG Xinyu,ZOU Zhenhong,LI Zhiwei,et al.Deep multi-modal fusion in object detection for autonomous driving[J].CAAI Transactions on Intelligent Systems,2020,15():758.[doi:10.11992/tis.202002010]
[5]陈玲玲,毕晓君.多模态融合网络的睡眠分期研究[J].智能系统学报,2022,17(6):1194.[doi:10.11992/tis.202202018]
CHEN Lingling,BI Xiaojun.Sleep staging model based on multimodal fusion[J].CAAI Transactions on Intelligent Systems,2022,17():1194.[doi:10.11992/tis.202202018]
[6]丁维昌,施俊,王骏.自监督对比特征学习的多模态乳腺超声诊断[J].智能系统学报,2023,18(1):66.[doi:10.11992/tis.202111052]
DING Weichang,SHI Jun,WANG Jun.Multi-modality ultrasound diagnosis of the breast with self-supervised contrastive feature learning[J].CAAI Transactions on Intelligent Systems,2023,18():66.[doi:10.11992/tis.202111052]
[7]亢洁,刘威.特征融合的装修案例跨模态检索方法[J].智能系统学报,2024,19(2):429.[doi:10.11992/tis.202207030]
KANG Jie,LIU Wei.A cross-modal retrieval algorithm of decoration cases on feature fusion[J].CAAI Transactions on Intelligent Systems,2024,19():429.[doi:10.11992/tis.202207030]
备注/Memo
收稿日期:2014-5-28;改回日期:。
基金项目:国家自然科学基金资助项目(61035003,61175042).
作者简介:张媛媛,女,1991年生,硕士研究生,主要研究方向为机器视觉、机器学习等;杨婉琪,女,1988年生,博士研究生,主要研究方向为机器学习、机器视觉等;高阳,男,1972年生,教授,博士生导师,主要研究方向为强化学习、智能agent、智能应用等。
通讯作者:张媛媛.E-mail:zhangyuanyuan2013nju@gmail.com.
更新日期/Last Update:
2015-06-15