浏览全部资源
扫码关注微信
Published： 16 May 2023 ，
移动端阅览
陈英， 吴文强， 徐亮， 郭书斌. 2023. 融合虹膜—眼周特征的非协作身份认证. 中国图象图形学报， 28(05):1462-1476
Chen Ying， Wu Wenqiang， Xu Liang， Guo Shubin. 2023. Iris-periocular features-fused non-collaborative authentication. Journal of Image and Graphics， 28(05):1462-1476
目的
2
虹膜识别是具有发展前景的生物特征认证方式，然而现有的一些方法无法在远距离、非协作状态下捕获的低质量图像中表现出较好的性能，极大阻碍了虹膜识别在实际中的应用部署。为此，提出一种基于卷积神经网络的网络模型，使用眼周和虹膜进行有效融合，克服单一模态生物特征的局限性，增强生物特征身份认证方式的可靠性和安全性。
方法
2
为了能够提取鲁棒性更强的辨别特征，将空间注意力机制和特征重用方法进行结合，有效减轻了在前向传播过程中梯度消失的问题。同时，引入中间融合表达层，根据不同模态低、中、高层特征信息对融合策略产生的贡献值自适应地学习相对应的权重，并通过加权组合的方式有效地融合生成鲁棒性更强的辨别特征，极大提升了虹膜识别在远距离、非协作状态下的识别性能。
结果
2
在3个公开数据集ND-IRIS-0405（notre dame）、CASIA（Institute of Automation，Chinese Academy of Sciences）-Iris-M1-S3以及CASIA-Iris-Distance上进行测试，本文方法EER（equal error rate）值分别为0.19%，0.48%，1.33%，优于对比方法，表明了本文方法的优越性。
结论
2
本文提出的中间融合表达层融合方法能够有效融合眼周和虹膜在不同阶段的语义信息，生成判别性更强的特征模板，提升了远距离、非协作状态下虹膜识别的性能。
Objective
2
Identity authentication method is in relevance with the biological characteristics of the human body， which is benefited from breakthrough of computer technology and consistent improvement of hardware computing ability in the past 20 years. The biometrics-relevant artificial intelligence （AI） technology has been developed intensively. Iris-related features analysis is crucial for biometric authentication method. Current iris recognition technique is used to optimize short-distance and specific scenarios， but it is still challenged for the applications in the context of long-distance and non-collaborative scenarios. There are two main constraints as mentioned below： first， the iris recognition process is required for a short distance-relevant sensor-based instruction in terms of matching-completed prompts. This acquisition process is challenged for large-scale application farther. Second， current sensor-based hardware acquisition is increased as the distance between target and acquisition device. The accuracy and reliability of recognition will be lower severely because the quality of iris image-gathered is not effective. The iris recognition performance is required to be improved for long-distance and low-quality images and non-prompted scenes. To get credible identity authentication， a variety of biometrics are focused on iris recognition-assisted. Multiple modal-fused biometric information is more effective compared to single modality based identification. First， due to the heterogeneity of biological characteristics， a variety of modes of biometric recognition needs to be mutual-benefited. Second， safe authentication methods will not be guaranteed effectively when the biometric information storage encounters information leakage. To meet the needs of iris recognition in real scenario， it is necessary to generate richer biometric information in the eye area of the human face， such as the iris and eye area. Eye area-related semantic information has good recognizability for identity identification， but the eye area recognition is disturbed easily by complex background information. The iris texture features are relatively stable and iris recognition is affected less. Therefore， to get accurate and stable authentication in non-prompted and long-distance scenarios， effective fusion of the eye circumference and iris can be optimized to achieve modalities-mutual benefits and enhance the reliability and security of biometric identity authentication.
Method
2
Some of the existing methods pay more attention on the high-dimensional semantic feature layer. To fuse the feature vectors of different modes， addition， multiplication and other related ways are then used. Due to great limitations， lack of certain flexibility and adaptability， the differences and the semantic characteristics of each mode are ignored at different stages. It is ineffective to combine multimode information of different stages mutually. To extract more robusted and distinctive features， the spatial attention mechanism and feature- reused method are coordinated and the model-opted can be focused on the feasible iris texture area， and the problem of gradient disappearance is alleviated via propagation-forward. For fusion strategy， the introduction of intermediate fusion expression layer can be adaptively used to learn the corresponding weights according to the contribution value of low， medium and high-level feature information of different modes， and it can be fused to generate more robust and distinctive features in terms of the integrated weights， which can improve the recognition performance of iris recognition in long-distance and non-cooperative status.
Result
2
To verify the effectiveness of the proposed method， experiments are carried out and compared to three popular public datasets， called notre dame （ND）-IRIS-0405， Institute of Automation，Chinese Academy of Sciences （CASIA）-Iris-M1-S3， and CASIA-Iris-Distance. Comparative analysis is in comparison with other related state-of-the-arts methods， including false reject rate （FRR）， true accept rate （TAR）， and equal error rate （EER）. Lower FRR and EER values can indicate better performance， while TAR is vice versa. The test results of the three publicly available datasets can demonstrate that each EER value can be optimized and reached to 0.19%， 0.48% and 1.33%.
Conclusion
2
We develop a convolutional neural network （CNN） based model. The model is focused on the iris texture area in terms of the integration of efficient channel attention mechanism and feature-reused and the problem of model gradient disappearance can be alleviated to a certain extent， which is beneficial for the depth of the model and robust distinctive features. At the same time， the intermediate fusion joint expression layer is introduced and focused on characteristics of semantic features of different modes at different stages， and it can learn the corresponding weights adaptively according to the degree of contribution generated by the low， medium and high semantic features of different modes， and the iris and eye area features are fused into distinctive features more through weighted fusion， which can improve the iris recognition performance in long-distance and non-cooperative status. This method is easy to be trainable as well.
虹膜识别眼周识别中间融合表达层自适应加权生物特征融合远距离和非协作
iris recognitionperiocular recognitioncentral fusion expression layeradaptive weightingbiometric fusionlong-distance and non-cooperative
Ahmad S and Fuller B. 2019. ThirdEye： triplet based iris recognition without normalization//Proceedings of the 10th IEEE International Conference on Biometrics Theory， Applications and Systems （BTAS）. Tampa， USA： IEEE： 1-9 ［DOI： 10.1109/BTAS46853.2019.9185998http://dx.doi.org/10.1109/BTAS46853.2019.9185998］
Ahuja K， Islam R， Barbhuiya F A and Dey K. 2016. A preliminary study of CNNs for iris and periocular verification in the visible spectrum//Proceedings of the 23rd International conference on pattern recognition （ICPR）. Cancun， Mexico： IEEE： 181-186 ［DOI： 10.1109/ICPR.2016.7899630http://dx.doi.org/10.1109/ICPR.2016.7899630］
Algashaam F， Nguyen K， Banks J， Chandran V， Do T A and Alkanhal M. 2021. Hierarchical fusion network for periocular and iris by neural network approximation and sparse autoencoder. Machine Vision and Applications， 32（1）： #15 ［DOI： 10.1007/s00138-020-01140-yhttp://dx.doi.org/10.1007/s00138-020-01140-y］
Brito J and Proença H. 2021. A deep adversarial framework for visually explainable periocular recognition//Proceedings of 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. Nashville， USA： IEEE： 1453-1461 ［DOI： 10.1109/CVPRW53098.2021.00161http://dx.doi.org/10.1109/CVPRW53098.2021.00161］
Chen J F. 2019. A Deep Learning Based Iris Recognition System. Xiamen： Xiamen University
陈剑峰. 2019. 基于深度学习的虹膜识别系统. 厦门： 厦门大学
Chen Y， Gan H M， Zeng Z and Chen H L. 2022. DADCNet： Dual attention densely connected network for more accurate real iris region segmentation. International Journal of Intelligent Systems， 37（1）： 829-858 ［DOI： 10.1002/int.22649http://dx.doi.org/10.1002/int.22649］
Chen Y， Zeng Z， Gan H M， Zeng Y G and Wu W Q. 2021a. Non-segmentation frameworks for accurate and robust iris recognition. Journal of Electronic Imaging， 30（3）： #033002 ［DOI： 10.1117/1.JEI.30.3.033002http://dx.doi.org/10.1117/1.JEI.30.3.033002］
Chen Y F， Wu C and Wang Y M. 2021b. Whether normalized or not？ Towards more robust iris recognition using dynamic programming. Image and Vision Computing， 107： #104112 ［DOI： 10.1016/j.imavis.2021.104112http://dx.doi.org/10.1016/j.imavis.2021.104112］
Choudhary M， Tiwari V and Venkanna U. 2020. Enhancing human iris recognition performance in unconstrained environment using ensemble of convolutional and residual deep neural network models. Soft Computing， 24（15）： 11477-11491 ［DOI： 10.1007/s00500-019-04610-2http://dx.doi.org/10.1007/s00500-019-04610-2］
Daugman J G. 1993. High confidence visual recognition of persons by a test of statistical independence. IEEE Transactions on Pattern Analysis and Machine Intelligence， 15（11）： 1148-1161 ［DOI： 10.1109/34.244676http://dx.doi.org/10.1109/34.244676］
Gangwar A， Joshi A， Joshi P and Raghavendra R. 2019. DeepIrisNet2： learning deep-IrisCodes from scratch for segmentation-robust visible wavelength and near infrared iris recognition ［EB/OL］. ［2022-06-24］. https：//arxiv.org/pdf/1902.05390.pdfhttps://arxiv.org/pdf/1902.05390.pdf
Jia D D and Shen W Z. 2022. IrisCodeNet： iris feature coding network. Computer Engineering and Applications， 58（10）： 185-192
贾丁丁， 沈文忠. 2022. IrisCodeNet： 虹膜特征编码网络. 计算机工程与应用， 58（10）： 185-192 ［DOI： 10.3778/j.issn.1002-8331.2011-0466http://dx.doi.org/10.3778/j.issn.1002-8331.2011-0466］
Kumar A and Passi A. 2010. Comparison and combination of iris matchers for reliable personal authentication. Pattern Recognition， 43（3）： 1016-1026 ［DOI： 10.1016/j.patcog.2009.08.016http://dx.doi.org/10.1016/j.patcog.2009.08.016］
Liu M K， Wang H M， Li Q and Sun Z N. 2020. Enhanced gray-level image space for iris liveness detection. Journal of Image and Graphics， 25（7）： 1421-1435
刘明康， 王宏民， 李琦， 孙哲南. 2020. 增强型灰度图像空间实现虹膜活体检测. 中国图象图形学报， 25（7）： 1421-1435 ［DOI： 10.11834/jig.190503http://dx.doi.org/10.11834/jig.190503］
Liu N F， Zhang M， Li H Q， Sun Z N and Tan T N. 2016. DeepIris： learning pairwise filter bank for heterogeneous iris verification. Pattern Recognition Letters， 82： 154-161 ［DOI： 10.1016/j.patrec.2015.09.016http://dx.doi.org/10.1016/j.patrec.2015.09.016］
Lumini A and Nanni L. 2017. Overview of the combination of biometric matchers. Information Fusion， 33： 71-85 ［DOI： 10.1016/j.inffus.2016.05.003http://dx.doi.org/10.1016/j.inffus.2016.05.003］
Luo Z D， Li J T and Zhu Y S. 2021. A deep feature fusion network based on multiple attention mechanisms for joint iris-periocular biometric recognition. IEEE Signal Processing Letters， 28： 1060-1064 ［DOI： 10.1109/LSP.2021.3079850http://dx.doi.org/10.1109/LSP.2021.3079850］
Mishra N K， Kumar S and Singh S K. 2022. MmLwThV framework： a masked face periocular recognition system using thermo-visible fusion. Applied Intelligence， 2023，53（3）： 2471-2487 ［DOI： 10.1007/s10489-022-03517-0http://dx.doi.org/10.1007/s10489-022-03517-0］
Monro D M， Rakshit S and Zhang D X. 2007. DCT-based iris recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence， 29（4）： 586-595 ［DOI： 10.1109/TPAMI.2007.1002http://dx.doi.org/10.1109/TPAMI.2007.1002］
Nguyen K， Fookes C， Jillela R， Sridharan S and Ross A. 2017. Long range iris recognition： a survey. Pattern Recognition， 72： 123-143 ［DOI： 10.1016/j.patcog.2017.05.021http://dx.doi.org/10.1016/j.patcog.2017.05.021］
Nie L， Kumar A and Zhan S. 2014. Periocular recognition using unsupervised convolutional RBM feature learning//Proceedings of the 22nd International Conference on Pattern Recognition. Stockholm， Sweden： IEEE： 399-404 ［DOI： 10.1109/ICPR.2014.77http://dx.doi.org/10.1109/ICPR.2014.77］
Nirgude M A and Gengaje S R. 2022. Iris recognition system based on convolutional neural network//ICT with Intelligent Applications. Singapore， Singapore： Springer： 455-463 ［DOI： 10.1007/978-981-16-4177-0_46http://dx.doi.org/10.1007/978-981-16-4177-0_46］
Park U， Ross A and Jain A K. 2009. Periocular biometrics in the visible spectrum： a feasibility study//Proceedings of the 3rd IEEE International Conference on Biometrics： Theory， Applications， and Systems. Washington， USA： IEEE： 1-6 ［DOI： 10.1109/BTAS.2009.5339068http://dx.doi.org/10.1109/BTAS.2009.5339068］
Phillips P J， Scruggs W T， O’Toole A J， Flynn P J， Bowyer K W， Schott C L and Sharpe M. 2010. FRVT 2006 and ICE 2006 large-scale experimental results. IEEE Transactions on Pattern Analysis and Machine Intelligence， 32（5）： 831-846 ［DOI： 10.1109/TPAMI.2009.59http://dx.doi.org/10.1109/TPAMI.2009.59］
Proenca H and Neves J C. 2018. Deep-PRWIS： periocular recognition without the iris and sclera using deep learning frameworks. IEEE Transactions on Information Forensics and Security， 13（4）： 888-896 ［DOI： 10.1109/TIFS.2017.2771230http://dx.doi.org/10.1109/TIFS.2017.2771230］
Raffei A F M， Sutikno T， Asmuni H， Hassan R， Othman R M， Kasim S and Riyadi M A. 2019. Fusion iris and periocular recognitions in non-cooperative environment. Indonesian Journal of Electrical Engineering and Informatics， 7（3）： 543-554 ［DOI： 10.52549/ijeei.v7i3.1147http://dx.doi.org/10.52549/ijeei.v7i3.1147］
Santos G， Grancho E， Bernardo M V and Fiadeiro P T. 2015. Fusing iris and periocular information for cross-sensor recognition. Pattern Recognition Letters， 57： 52-59 ［DOI： 10.1016/j.patrec.2014.09.012http://dx.doi.org/10.1016/j.patrec.2014.09.012］
Smereka J M， Boddeti V N and Kumar B V K V. 2015. Probabilistic deformation models for challenging periocular image verification. IEEE Transactions on Information Forensics and Security， 10（9）： 1875-1890 ［DOI： 10.1109/TIFS.2015.2434271http://dx.doi.org/10.1109/TIFS.2015.2434271］
Sun Z N， He R， Wang L， Kan M N， Feng J J， Zheng F， Zheng W S， Zuo W M， Kang W X， Deng W H， Zhang J， Han H， Shan S G， Wang Y L， Ru Y W， Zhu Y H， Liu Y F and He Y. 2021. Overview of biometrics research. Journal of Image and Graphics， 26（6）： 1254-1329
孙哲南， 赫然， 王亮， 阚美娜， 冯建江， 郑方， 郑伟诗， 左旺孟， 康文雄， 邓伟洪， 张杰， 韩琥， 山世光， 王云龙， 茹一伟， 朱宇豪， 刘云帆， 何勇. 2021. 生物特征识别学科发展报告. 中国图象图形学报， 26（6）： 1254-1329 ［DOI： 10.11834/jig.210078http://dx.doi.org/10.11834/jig.210078］
Talreja V， Nasrabadi N M and Valenti M C. 2022. Attribute-based deep periocular recognition： leveraging soft biometrics to improve periocular recognition//Proceedings of 2022 IEEE/CVF Winter Conference on Applications of Computer Vision. Waikoloa， USA： IEEE： 1141-1150 ［DOI： 10.1109/WACV51458.2022.00121http://dx.doi.org/10.1109/WACV51458.2022.00121］
Tan C W and Kumar A. 2013. Towards online iris and periocular recognition under relaxed imaging constraints. IEEE Transactions on Image Processing， 22（10）： 3751-3765 ［DOI： 10.1109/TIP.2013.2260165http://dx.doi.org/10.1109/TIP.2013.2260165］
Tan D T， Li S C， Chang W W and Li D L. 2020. Multi-feature fusion behavior recognition model. Journal of Image and Graphics， 25（12）： 2541-2552
谭等泰， 李世超， 常文文， 李登楼. 2020. 多特征融合的行为识别模型. 中国图象图形学报， 25（12）： 2541-2552 ［DOI： 10.11834/jig.190637http://dx.doi.org/10.11834/jig.190637］
Tan T N. 2018. CASIA.v4 database ［DB/OL］. ［2022-06-01］. http：//biometrics.idealtest.orghttp://biometrics.idealtest.org
Verma S， Mittal P， Vatsa M and Singh R. 2016. At-a-distance person recognition via combining ocular features//Proceedings of 2016 IEEE International Conference on Image Processing （ICIP）. Phoenix， USA： IEEE： 3131-3135 ［DOI： 10.1109/ICIP.2016.7532936http://dx.doi.org/10.1109/ICIP.2016.7532936］
Vyas R. 2022. Enhanced near-infrared periocular recognition through collaborative rendering of hand crafted and deep features. Multimedia Tools and Applications， 81（7）： 9351-9365 ［DOI： 10.1007/s11042-021-11846-4http://dx.doi.org/10.1007/s11042-021-11846-4］
Wang K and Kumar A. 2021. Periocular-assisted multi-feature collaboration for dynamic iris recognition. IEEE Transactions on Information Forensics and Security， 16： 866-879 ［DOI： 10.1109/TIFS.2020.3023289http://dx.doi.org/10.1109/TIFS.2020.3023289］
Wang Q L， Wu B G， Zhu P F， Li P H， Zuo W M and Hu Q H. 2020. ECA-Net： efficient channel attention for deep convolutional neural networks//Proceedings of 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition （CVPR）. Seattle， USA： IEEE： 11531-11539 ［DOI： 10.1109/CVPR42600.2020.01155http://dx.doi.org/10.1109/CVPR42600.2020.01155］
Wang Y L， Ma J， Li H Q， Zhang M and Sun Z N. 2018. Race classification based on deep features and Fisher vectors of iris texture. Journal of Image and Graphics， 23（1）： 28-38
王雅丽， 马静， 李海青， 张曼， 孙哲南. 2018. 基于虹膜纹理深度特征和Fisher向量的人种分类. 中国图象图形学报， 23（1）： 28-38 ［DOI： 10.11834/jig.170219http://dx.doi.org/10.11834/jig.170219］
Xu S， Zheng F， Tang J and Bao W X. 2022. Dual branch feature fusion network based gait recognition algorithm. Journal of Image and Graphics， 27（7）： 2263-2273
徐硕， 郑锋， 唐俊， 鲍文霞. 2022. 双分支特征融合网络的步态识别算法. 中国图象图形学报， 27（7）： 2263-2273 ［DOI： 10.11834/jig.200730http://dx.doi.org/10.11834/jig.200730］
Yang K， Xu Z H and Fei J J. 2021. DualSANet： dual spatial attention network for iris recognition//Proceedings of 2021 IEEE Winter Conference on Applications of Computer Vision. Waikoloa， USA： IEEE： 888-896 ［DOI： 10.1109/WACV48630.2021.00093http://dx.doi.org/10.1109/WACV48630.2021.00093］
Zhang Q， Li H Q， Sun Z N and Tan T N. 2018. Deep feature fusion for iris and periocular biometrics on mobile devices. IEEE Transactions on Information Forensics and Security， 13（11）： 2897-2912 ［DOI： 10.1109/TIFS.2018.2833033http://dx.doi.org/10.1109/TIFS.2018.2833033］
Zhang Z L， Zhang H， Wang J， Xia Y F， Liu L， Li P P and He Z F. 2022. Region attention mechanism based dual human iris completion technology. Journal of Image and Graphics， 27（5）： 1669-1681
张志礼， 张慧， 王甲， 夏玉峰， 刘亮， 李佩佩， 何召锋. 2022. 区域注意力机制引导的双路虹膜补全. 中国图象图形学报， 27（5）： 1669-1681 ［DOI： 10.11834/jig.210795http://dx.doi.org/10.11834/jig.210795］
Zhao Z J and Kumar A. 2017a. Towards more accurate iris recognition using deeply learned spatially corresponding features//Proceedings of 2017 IEEE International Conference on Computer Vision. Venice， Italy： IEEE： 3829-3838 ［DOI： 10.1109/ICCV.2017.411http://dx.doi.org/10.1109/ICCV.2017.411］
Zhao Z J and Kumar A. 2017b. Accurate periocular recognition under less constrained environment using semantics-assisted convolutional neural network. IEEE Transactions on Information Forensics and Security， 12（5）： 1017-1030 ［DOI： 10.1109/TIFS.2016.2636093http://dx.doi.org/10.1109/TIFS.2016.2636093］
Zhao Z J and Kumar A. 2018. Improving periocular recognition by explicit attention to critical regions in deep neural network. IEEE Transactions on Information Forensics and Security， 13（12）： 2937-2952 ［DOI： 10.1109/TIFS.2018.2833018http://dx.doi.org/10.1109/TIFS.2018.2833018］
Zhao Z J and Kumar A. 2019. A deep learning based unified framework to detect， segment and recognize irises using spatially corresponding features. Pattern Recognition， 93： 546-557 ［DOI： 10.1016/j.patcog.2019.04.010http://dx.doi.org/10.1016/j.patcog.2019.04.010］
相关文章
相关作者
相关机构
京公网安备11010802024621