Abstract:Deep learning-based methods show excellent recognition performance and potential in finger vein recognition. However, due to the expensive training costs and differences in categories and distributions across different datasets, a model that performs well on one dataset may struggle to efficiently adapt to new data or perform poorly on new data. A fast transferable model for cross-dataset finger vein recognition, including a two-stage solution, is proposed to realize high efficient application of model on different datasets with good performance in practical scenarios where recognition systems are applied to various user groups and devices. Firstly, in the first stage, a domain adaptation algorithm based on feature alignment and clustering is introduced to guide the network in extracting discriminative and robust features, aiming to obtain a deep model that can generalize well on unseen target data. Secondly, a bias field correction network is developed to reduce dataset gaps caused by bias fields in images and further adjust the latent distribution to make the datasets more similar to each other. Then, in the second stage of fast transfer, a modified classifier based on extreme learning machine with a faster learning speed is designed to accelerate model transfer training and make full use of the template information of new data.Experimental results on four public finger vein databases show that the proposed method realizes efficient transfer and achieves recognition performance as good as the best end-to-end training method dose in the target task. For common application scenarios, the proposed method can meet the requirements of real-time deployment and provide a feasible solution for the application of deep learning techniques in cross-dataset finger vein recognition.
[1] HOU B R, ZHANG H J, YAN R Q. Finger-Vein Biometric Recognition: A Review. IEEE Transactions on Instrumentation and Mea-surement, 2022, 71. DOI: 10.1109/TIM.2022.3200087. [2] SHAHEED K, MAO A H, QURESHI I, et al. Recent Advancements in Finger Vein Recognition Technology: Methodology, Cha-llenges and Opportunities. Information Fusion, 2022, 79: 84-109. [3] YIN X F, ZHU Y M, HU J K. Contactless Fingerprint Recognition Based on Global Minutia Topology and Loose Genetic Algorithm. IEEE Transactions on Information Forensics and Security, 2020, 15: 28-41. [4] DING C X, TAO D C. Trunk-Branch Ensemble Convolutional Neural Networks for Video-Based Face Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 40(4): 1002-1014. [5] QIN H F, EL-YACOUBI M A. Deep Representation-Based Feature Extraction and Recovering for Finger-Vein Verification. IEEE Transactions on Information Forensics and Security, 2017, 12(8): 1816-1829. [6] FANG Y X, WU Q X, KANG W X. A Novel Finger Vein Verification System Based on Two-Stream Convolutional Network Learning. Neurocomputing, 2018, 290:100-107. [7] SHEN J Q, LIU N Z, XU C L, et al. Finger Vein Recognition Algorithm Based on Lightweight Deep Convolutional Neural Network. IEEE Transactions on Instrumentation and Measurement, 2022, 71. DOI: 10.1109/TIM.2021.3132332. [8] HUANG Z, GUO C A. Robust Finger Vein Recognition Based on Deep CNN with Spatial Attention and Bias Field Correction. International Journal of Artificial Intelligence Tools, 2021, 30(1). DOI: 10.1142/s0218213021400054. [9] MA B, WANG K X, HU Y L. Finger Vein Recognition Based on Bilinear Fusion of Multiscale Features. Scientific Reports, 2023, 13(1). DOI: 10.1038/s41598-023-27524-4. [10] SHAHEED K, MAO A H, QURESHI I, et al. DS-CNN: A Pre-trained Xception Model Based on Depth-Wise Separable Convolutional Neural Network for Finger Vein Recognition. Expert Systems with Applications, 2022, 191. DOI: 10.1016/j.eswa.2021.11628. [11] TORRALBA A, EFROS A A. Unbiased Look at Dataset Bias // Proc of the IEEE Conference on Computer Vision and Pattern Re-cognition. Washington, USA: IEEE, 2011: 1521-1528. [12] SZE V, CHEN Y H, YANG T J, et al. Efficient Processing of Deep Neural Networks: A Tutorial and Survey. Proceedings of the IEEE, 2017, 105(12): 2295-2329. [13] ZHAO S C, YUE X Y, ZHANG S H, et al. A Review of Single-Source Deep Unsupervised Visual Domain Adaptation. IEEE Transactions on Neural Networks and Learning Systems, 2022, 33(2): 473-493. [14] DENG W X, LIAO Q, ZHAO L J, et al. Joint Clustering and Discriminative Feature Alignment for Unsupervised Domain Adaptation. IEEE Transactions on Image Processing, 2021, 30: 7842-7855. [15] DUBEY A, RAMANATHAN V, PENTLAND A, et al. Adaptive Methods for Real-World Domain Generalization // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 14335-14344. [16] LI S, LIU C H, LIN Q X, et al. Deep Residual Correction Network for Partial Domain Adaptation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, 43(7): 2329-2344. [17] HUANG J T, LI J Y, YU D, et al. Cross-Language Knowledge Transfer Using Multilingual Deep Neural Network with Shared Hi-dden Layer // Proc of the IEEE International Conference on Acoustics, Speech and Signal Processing. Washington, USA: IEEE, 2013: 7304-7308. [18] OQUAB M, BOTTOU L, LAPTEV I, et al. Learning and Transfe-rring Mid-level Image Representations Using Convolutional Neural Networks // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2014: 1717-1724. [19] HUANG G B, ZHU Q Y, SIEW C K. Extreme Learning Machine: Theory and Applications. Sensors, 2006, 70(1/2/3): 489-501. [20] HONG H G, LEE M B, PARK K R. Convolutional Neural Network-Based Finger-Vein Recognition Using NIR Image Sensors. Sensors, 2017, 17(6). DOI: 10.3390/s17061297. [21] TANG S, ZHOU S, KANG W X. Finger Vein Verification Using a Siamese CNN. IET Biometrics, 2019, 8(5): 306-315. [22] YANG W M, HUI C Q, CHEN Z Q, et al. FV-GAN: Finger Vein Representation Using Generative Adversarial Networks. IEEE Transactions on Information Forensics and Security, 2019, 14(9): 2512-2524. [23] XIE C H, KUMAR A. Finger Vein Identification Using Convolutional Neural Network and Supervised Discrete Hashing. Pattern Recognition Letters, 2019, 119: 148-156. [24] LU Y, XIE S J, WU S Q. Exploring Competitive Features Using Deep Convolutional Neural Network for Finger Vein Recognition. IEEE Access, 2019, 7: 35113-35123. [25] HOU B R, YAN R Q. Triplet-Classifier GAN for Finger-Vein Verification. IEEE Transactions on Instrumentation and Measurement, 2022, 71. DOI: 10.1109/TIM.2022.3154834. [26] RADZI S A, KHALIL-HANI M, BAKHTERI R. Finger-Vein Biometric Identification Using Convolutional Neural Network. Turkish Journal of Electrical Engineering and Computer Sciences, 2016, 24(3): 1863-1878. [27] DAS R, PICIUCCO E, MAIORANA E, et al. Convolutional Neural Network for Finger-Vein-Based Biometric Identification. IEEE Transactions on Information Forensics and Security, 2019, 14(2): 360-373. [28] WANG G Q, SUN C M, SOWMYA A. Learning a Compact Vein Discrimination Model with Generated Samples. IEEE Transactions on Information Forensics and Security, 2020, 15: 635-650. [29] BOUCHERIT I, ZMIRLI M O, HENTABLI H, et al. Finger Vein Identification Using Deeply-Fused Convolutional Neural Network. Journal of King Saud University-Computer and Information Sciences, 2022, 34(3): 646-656. [30] RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutio-nal Networks for Biomedical Image Segmentation // Proc of the International Conference on Medical Image Computing and Computer-Assisted Intervention. Berlin, Germany: Springer, 2015: 234-241. [31] SIMONYAN K, ZISSERMAN A.Very Deep Convolutional Networks for Large-Scale Image Recognition[C/OL]. [2023-04-23].https://arxiv.org/abs/1409.1556. [32] HE K M, ZHANG X Y, REN S Q, et al. Deep Residual Learning for Image Recognition // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2016: 770-778. [33] CHEN X L, HE K M. Exploring Simple Siamese Representation Learning // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2021: 15745-15753. [34] PENROSE R. A Generalized Inverse for Matrices. Mathematical Proceedings of the Cambridge Philosophical Society, 1955, 57(3): 406-413. [35] BARTLETT P L. The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights Is More Important Than the Size of the Network. IEEE Transactions on Information Theory, 1998, 44(2): 525-536. [36] YIN Y L, LIU L L, SUN X W. SDUMLA-HMT: A Multimodal Biometric Database // Proc of the Chinese Conference on Biometric Recognition. Berlin, Germany: Springer, 2011: 260-268. [37] YANG W M, YU X, LIAO Q M. Personal Authentication Using Finger Vein Pattern and Finger-Dorsa Texture Fusion // Proc of the 17th ACM International Conference on Multimedia. New York, USA: ACM, 2009: 905-908. [38] ASAARI M S M, SUANDI S A, ROSDI B A. Fusion of Band Li-mited Phase Only Correlation and Width Centroid Contour Distance for Finger Based Biometrics. Expert Systems with Applications, 2014, 41(7): 3367-3382. [39] KUMAR A, ZHOU Y B. Human Identification Using Finger Images. IEEE Transactions on Image Processing, 2012, 21(4): 2228-2244. [40] MIURA N, NAGASAKA A, MIYATAKE T. Feature Extraction of Finger Vein Patterns Based on Repeated Line Tracking and Its Application to Personal Identification. Machine Vision and Applications, 2004, 15(4): 194-203. [41] MIURA N, NAGASAKA A, MIYATAKE T. Extraction of Finger-Vein Patterns Using Maximum Curvature Points in Image Profiles. IEICE Transactions on Information and Systems, 2007, E90-D(8): 1185-1194. [42] HUANG B N, DAIRY Y G, LI R F, et al. Finger-Vein Authentication Based on Wide Line Detector and Pattern Normalization // Proc of the 20th International Conference on Pattern Recognition. New York, USA: ACM, 2010: 1269-1272. [43] YANG L, YANG G P, WANG K K, et al. Finger Vein Recognition via Sparse Reconstruction Error Constrained Low-Rank Representation. IEEE Transactions on Information Forensics and Security, 2021, 16: 4869-4881. [44] MA H, HU N, FANG C X. The Biometric Recognition System Based on Near-Infrared Finger Vein Image. Infrared Physics and Technology, 2021, 115. DOI: 10.1016/j.infrared.2021.103734. [45] WANG Z L, WU D H, GRAVINA R, et al. Kernel Fusion Based Extreme Learning Machine for Cross-Location Activity Recognition. Information Fusion, 2017, 37(C). DOI: 10.1016/j.inffus.2017.01.004.