Abstract
In the context of the spread of the new crown epidemic, periocular recognition has become an effective alternative in less constrained environments where the face is inconvenient to obtain. Although the periocular recognition algorithms based on deep learning have made great progress, the network performance is expected to be further improved with fewer parameters in the practical applications. In this work, we proposed a lightweight CNN based on the combination of an attention mechanism and mid-level features, referred to as AttenMidNet. This attention module is directly inserted into the convolution blocks at all levels to adaptively assign weights to the feature channels to obtain the mid-level features with the most information. Then the mid-level features at all levels are contacted to form the final feature representation vector. This method not only expresses the features more comprehensively, but also drastically reduces the number of network parameters. The experimental results using within-dataset and cross-dataset evaluation on three publicly available datasets (UBIRIS.v2, CASIA_Iris_Distance, CASIA_Iris_Twins, and one self-collected periocular dataset) have proved the effectiveness of the proposed network. Moreover, a compact and efficient periocular recognition system including access control and mobile terminals was designed using the proposed network. In addition to the real-time detection and matching of periocular images, the access control terminal can also realize scanning and verification of QR code images. During the peak period of people flow, users can log in to the online periocular recognition system via the mobile terminal in advance for matching authentication. If successful, the corresponding QR code will be generated, through which to reduce crowd gathering time.
Similar content being viewed by others
Data availability
The datasets CASIA_Iris_Distance and Twins analysed used in this study are available in the CASIA-Iris-V4 repository, http://www.cbsr.ia.ac.cn/china/Iris%20Databases%20CH.asp. The dataset UBIRIS.v2 analysed is available in the UBIRIS repository, [iris.di.ubi.pt]. Our self-collected dataset is available from the corresponding author on reasonable request.
References
Abate A, Cimmino L, Nappi M et al (2022) Fusion of periocular deep features in a dual-input CNN for biometric recognition[C]. International conference on image analysis and processing (ICIAP), pp 368–378
Ai H, Cheng X (2018) Research on embedded access control security system and face recognition system[J]. Measurement 123:309–322
Almadan A, Rattani A (2021) Compact CNN models for on-device ocular-based user recognition in mobile devices[C]. 2021 IEEE symposium series on computational intelligence (SSCI). IEEE, pp 1–7
Behera SS, Mishra SS, Mandal B, Puhan NB (2020) Variance-guided attention-based twin deep network for cross-spectral periocular recognition[J]. Image Vis Comput 104:104016
Bharadwaj S, Bhatt HS, Vatsa M et al (2010) Periocular biometrics: when iris recognition fails[C]. 2010 fourth IEEE international conference on Biometrics: Theory, Applications and Systems (BTAS). IEEE, 2010, pp 1–6
CASIA Iris Image Database V4.0. http://www.cbsr.ia.ac.cn/china/Iris%20Databases%20CH.asp
Chen Q, Liu L, Han R et al (2019) Image identification method on high speed railway contact network based on YOLO v3 and SENet[C]. 2019 Chinese control conference (CCC). IEEE, pp 8772–8777
Gu R, Wang G, Song T, Huang R, Aertsen M, Deprest J, Ourselin S, Vercauteren T, Zhang S (2021) CA-net: comprehensive attention convolutional neural networks for explainable medical image segmentation[J]. IEEE Trans Med Imaging 40(2):699–711
He K, Zhang X, Ren S et al (2016) Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778
Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks[J]. Science 313(5786):504–507
Hu CH, Zhang Y, Wu F et al (2019) Toward driver face recognition in the intelligent traffic monitoring systems[J]. IEEE Trans Intell Transp Syst 21(12):4958–4971
Hu J, Shen L, Albanie S, Sun G, Wu E (2020) Squeeze-and-excitation networks[J]. IEEE Trans Pattern Anal Mach Intell 42(8):2011–2023
Hwang H, Lee EC (2020) Near-infrared image-based periocular biometric method using convolutional neural network[J]. IEEE Access 8:158612–158621
Im D, Han D, Choi S, Kang S, Yoo HJ (2020) DT-CNN: an energy-efficient dilated and transposed convolutional neural network processor for region of interest based image segmentation[J]. IEEE Trans Circuits-I 67(10):3471–3483
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift[C]. International conference on machine learning. PMLR, pp 448–456
Khan S, Akram A, Usman N (2020) Real time automatic attendance system for face recognition using face API and OpenCV[J]. Wirel Pers Commun 113(1):469–480
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks[J]. Adv Neural Inf Proces Syst:1097–1105
Kumari P, Seeja KR (2021) A novel periocular biometrics solution for authentication during Covid-19 pandemic situation[J]. J Ambient Intell Humaniz Comput 12:10321–10337
LeCun Y, Bottou L, Bengio Y et al (1998) Gradient-based learning applied to document recognition[J]. Proc IEEE 86(11):2278–2324
Lee DH (2021) CNN-based single object detection and tracking in videos and its application to drone detection[J]. Multimed Tools Appl 80(26):34237–34248
Li T, Leng J, Kong L, Guo S, Bai G, Wang K (2019) DCNR: deep cube CNN with random forest for hyperspectral image classification[J]. Multimed Tools Appl 78:3411–3433
Liangkui L, Shaoyou W, Zhongxing T (2018) Using deep learning to detect small targets in infrared oversampling images[J]. J Syst Eng Electron 29(5):947–952
Mahalingam G, Ricanek K (2013) LBP-based periocular recognition on challenging face datasets[J]. EURASIP J Image Video Process 2013(1):1–13
Mishra NK, Kumar S, Singh SK (2022) MmLwThV framework: a masked face periocular recognition system using thermo-visible fusion[J]. Appl Intell 2022:1–17
Molchanov P, Tyree S, Karras T et al (2016) Pruning convolutional neural networks for resource efficient inference[J]. arXiv preprint arXiv:1611.06440
Park U, Ross A, Jain AK (2009) Periocular biometrics in the visible spectrum: a feasibility study[C]. 2009 IEEE 3rd international conference on biometrics: theory, applications, and systems. IEEE, pp 1–6
Proença H (2014) Ocular biometrics by score-level fusion of disparate experts[J]. IEEE Trans Image Process 23(12):5082–5093
Proença H, Neves JC (2017) Deep-prwis: periocular recognition without the iris and sclera using deep learning frameworks[J]. IEEE Trans Inf Forensics Secur 13(4):888–896
Proença H, Filipe S, Santos R et al (2009) The UBIRIS. v2: a database of visible wavelength iris images captured on-the-move and at-a-distance[J]. IEEE Trans Pattern Anal Mach Intell 32(8):1529–1535
Qin J, Chen L, Liu Y, Liu C, Feng C, Chen B (2019) A machine learning methodology for diagnosing chronic kidney disease[J]. IEEE Access 8:20991–21002
Qin R, Fu X, Lang P (2020) PolSAR image classification based on low-frequency and contour subbands-driven polarimetric SENet[J]. IEEE J Sel Topics Appl Earth Observ Remote Sens 13:4760–4773
Reddy N, Rattani A, Derakhshani R (2020) Generalizable deep features for ocular biometrics[J]. Image Vis Comput 103:103996
Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) Imagenet large scale visual recognition challenge[J]. Int J Comput Vis 115(3):211–252
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556
Smereka JM, Boddeti VN, Kumar BVKV (2015) Probabilistic deformation models for challenging periocular image verification[J]. IEEE Trans Inf Forensics Secur 10(9):1875–1890
Smereka JM, Kumar BVKV, Rodriguez A (2016) Selecting discriminative regions for periocular verification[C]. International Conference on Identity, Security and Behavior Analysis (ISBA). IEEE, pp 1–8
Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1–9
Tan CW, Kumar A (2013) Towards online iris and periocular recognition under relaxed imaging constraints[J]. IEEE Trans Image Process 22(10):3751–3765
Umer S, Sardar A, Dhara BC, Rout RK, Pandey HM (2020) Person identification using fusion of iris and periocular deep features[J]. Neural Netw 122:407–419
Van Dyk DA, Meng XL (2001) The art of data augmentation[J]. J Comput Graph Stat 10(1):1–50
Wang K, Kumar A (2020) Periocular-assisted multi-feature collaboration for dynamic iris recognition[J]. IEEE Trans Inf Forensics Sec 16:866–879
Wang Z, Li C, Shao H, Sun J (2018) Eye recognition with mixed convolutional and residual network (MiCoRe-Net)[J]. IEEE Access 6:17905–17912
Williams S, Waterman A, Patterson D (2009) Roofline: an insightful visual performance model for multicore architectures[J]. Commun ACM 52(4):65–76
Zhao Z, Kumar A (2016) Accurate periocular recognition under less constrained environment using semantics-assisted convolutional neural network[J]. IEEE Trans Inf Forensics Sec 12(5):1017–1030
Zhao Z, Kumar A (2018) Improving periocular recognition by explicit attention to critical regions in deep neural network[J]. IEEE Trans Inf Forensics Sec 13(12):2937–2952
Acknowledgments
This study was supported by the National Nature Science Foundation of China [grant number 61801400] and JSPS KAKENHI [grant number JP18F18392]. At the same time, we would like to thank the SOCIA Lab, University of Beira Interior, Covilhã, Portugal and the Institute of Automation, Chinese Academy of Sciences, Beijing, China, for their contributions of the datasets employed in this work.
Author information
Authors and Affiliations
Contributions
All authors have made significant contributions to the research reported and have read and approved the submitted manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zou, Q., Wang, C., Yang, S. et al. A compact periocular recognition system based on deep learning framework AttenMidNet with the attention mechanism. Multimed Tools Appl 82, 15837–15857 (2023). https://doi.org/10.1007/s11042-022-14017-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-14017-1