Abstract
Local binary feature learning has attracted a lot of researches in image recognition due to its vital effectiveness. Generally, in the traditional local feature learning methods, a projection is learned to map the patches of image into binary features and then a codebook is generated by clustering the binary features with K-means clustering. However, these local feature learning methods, such as compact binary face descriptor and discriminative binary descriptor, ignore the category specific distributions of the original features during the feature learning process and use the real-valued clustering approach to generate the codebook, the discriminant of feature is degraded and the merits of binary feature are lost. To tack these problems, in this paper, we propose a novel category-preserving binary feature learning and binary codebook leaning (CPBFL-BCL) method for finger vein recognition. In CPBFL-BCL, the discrimination of learned binary features is generated by criteria of fisher discriminant analysis and category manifold preserving regularity during the feature learning process, and a novel binary clustering method based on K-means clustering is designed to generate binary codebook. Experimental results on recognition and retrieval tasks using two public finger vein databases are presented and demonstrate the effectiveness and efficiency of the proposed method over the state-of-the-art finger vein methods and a finger vein retrieval method.
Similar content being viewed by others
References
Michael G, Connie T, Teoh A (2011) A contactless biometric system using palm print and palm vein features. J Vis Commun Image Represent 23(7):155–178
Lu J, Erin L, Zhou J (2017) Simultaneous local binary feature learning and encoding for homogeneous and heterogeneous face recognition. IEEE Trans Pattern Anal Mach 40(8):1979–1993
Lee EC, Jung H, Kim D (2011) New finger biometric method using near infrared imaging. Sensors 11(3):2319–2333
Yang J, Zhang B, Shi Y (2012) Scattering removal for finger vein image restoration. Sensors 12(3):3627–3640
Shin K, Park Y, Nguyen D, Park K (2014) Finger vein image enhancement using a fuzzy-based fusion method with gabor and retinex filtering. Sensors 14(2):3095–3129
Yang L, Yang G, Yin Y, Xiao R (2013) Sliding window-based region of interest extraction for finger vein images. Sensors 13:3799–3815
Yang G, Xi X, Yin Y (2011) Finger vein recognition based on a personalized best bit map. Sensors 11:11357–11371
Liu F, Yin Y, Yang G, Dong L, Xi X (2014) Finger vein recognition with superpixel-based features. In: 2014 IEEE international joint conference on biometrics (IJCB). IEEE, pp 1–8
Yang L, Yang G, Yin Y, Xi X (2018) Finger vein recognition with anatomy structure analysis. IEEE Trans Circuits Syst Video Techn 28(8):1892–1905
Yang L, Yang G, Xi X, Su K, Chen Q, Yin Y (2018) Finger vein code: from indexing to matching. IEEE Trans Inf Forensics Secur 14(5):1210–1223
Dong L, Yang G, Yin Y, Xi X, Yang L, Liu F (2015) Finger vein verification with vein textons. Int J Pattern Recognit Artif Intell 29(4):1556003
Liu H, Yang L, Yang G, Yin Y (2018) Discriminative binary descriptor for finger vein recognition. IEEE Access 6:5795–5804
Rosdi BA, Shing CW, Suandi SA (2011) Finger vein recognition using local line binary pattern. Sensors 11(12):11357–11371
Lu Y, Xie SJ, Yoon S, Park DS (2013) Finger vein identification using polydirectional local line binary pattern. In: ICT convergence (ICTC). IEEE, pp 61–65
Faudzi SAAM, Yahya N (2014) Evaluation of LBP-based face recognition techniques. In: 2014 5th International conference on intelligent and advanced systems (ICIAS). IEEE, pp 1–6
Lee HC, Nagasaka A, Miyatake T (2010) Finger vein recognition using weighted local binary pattern code based on a support vector machine. J Zhejiang Univ Sci C 11:514–524
Zhao G, Matti P (2007) Dynamic texture recognition using local binary patterns with an application to facial expressions. IEEE Trans Pattern Anal Mach 29(6):915–928
Liu L, Fieguth P, Guo Y, Wang X, Pietikainen M (2017) Local binary features for texture classification: taxonomy and experimental study. Pattern Recognit 62:135–160
Lu J, Liong VE, Zhou X, Jie Z (2015) Learning compact binary face descriptor for face recognition. IEEE Trans Pattern Anal Mach 37(10):2041–2056
Deng W, Hu J, Guo J (2019) Compressive binary patterns: designing a robust binary face descriptor with random-field eigenfilters. IEEE Trans Pattern Anal Mach 41(3):758–767
Xi X, Yang L, Yin Y (2017) Learning discriminative binary codes for finger vein recognition. Pattern Recogn 66:26–33
Dong F, Nie X, Liu X, Geng L, Wang Q (2018) Cross-modal hashing based on category structure preserving. J Vis Commun Image Represent 57:28–33
Fisher RA (1936) The use of multiple measurements in taxonomic problems. Ann Hum Genet 7(2):179–188
Irie G, Li Z, Wu X, Chang S (2014) Locally linear hashing for extracting non-linear manifolds. In: 2014 IEEE conference on computer vision and pattern recognition (CVPR), pp 2115–2122
Ji R, Liu H, Cao L, Liu D, Wu Y, Huang F (2017) Toward optimal manifold hashing via discrete locally linear embedding. IEEE Trans Image Process 26:5411–5420
Liu H, Yang G, Yang L, Su K, Yin Y (2019) Anchor-based manifold binary pattern for finger vein recognition. Sci China Inf Sci 62(2019):052104
Miura N, Nagasaka A, Miyatake T (2004) Feature extraction of finger vein pattern based on repeated line tracking and its application to personal identification. Mach Vis Appl 15(4):194–203
Miura N, Nagasaka A, Miyatake T (2007) Extraction of finger vein patterns using maximum curvature points in image profiles. IEICE Trans Inf Syst 90(8):1185–1194
Song W, Kim T, Kim HC, Choi JH, Kong HJ (2011) A finger vein verification system using mean curvature. Pattern Recognit Lett 32(11):1541–1547
Kumar A, Zhou Y (2012) Human identification using finger images. IEEE Trans Image Process 21(4):2228–2244
Yu C, Qin H, Zhang L, Cui Y (2009) Finger vein image recognition combining modified Hausdorff distance with minutiae feature matching. Interdiscip Sci Comput Life Sci 2(4):280–289
Matsuda Y, Miura N, Nagasaka A, Kiyomizu H, Miyatake T (2016) Finger-vein authentication based on deformation-tolerant feature-point matching. Mach Vis Appl 27(2):237–250
Wu J, Liu C (2011) Finger vein pattern identification using principal component analysis and the neural network technique. Expert Syst Appl 145:75–89
Yang G, Xi X, Yin Y (2011) Finger vein recognition based on (2D)\(^2\)PCA and metric learning. BioMed Res Int 2012(3):324249
Guan F, Wang K, Liu J, Wu Q (2011) Bi-direction weighted (2D)\(^2\)PCA with eigenvalue normalization one forefinger vein recognition. Pattern Recogn Art Intell 24:417–424
Wu J, Liu C (2011) Finger vein pattern identification using svm and neural network technique. Expert Syst Appl 38(11):14284–14289
Zhou L, Yang G, Yin Y, Yang L, Wang K (2016) Finger vein recognition based on stable and discriminative superpixels. Int J Pattern Recognit Artif Intell 30(6):1650015
Duan Y, Lu J, Feng J, Zhou J (2017) Learning rotation-invariant local binary descriptor. IEEE Trans Image Process 26(8):3636–3651
Duan Y, Lu J, Feng J (2018) Context-aware local binary feature learning for face recognition. IEEE Trans Pattern Anal Mach 40(5):1139–1153
Gong Y, Pawlowski M, Yang F, Brandy L, Bourdev L, Fergus R (2015) Web scale photo hash clustering on a single machine. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 19–27
Shen X, Liu W, Tsang I, Shen F, Sun Q (2017) Compressed K-means approach for large-scale clustering. In: Proceedings of the thirty-first AAAI conference on artificial intelligence (AAAI), pp 2527–2533
Zhang Z, Liu L, Shen F, Shen H, Shao L (2019) Binary multi-view clustering. IEEE Trans Pattern Anal Mach 41(7):1774–1782
Zhang Z, Liu L, Qin J, Zhu F, Shen H (2018) Highly-economized multi-view binary compression for scalable image clustering. In: European conference on computer vision (ECCV), pp 717–732
Lai Z, Chen Y, Wu J, Wai W, Shen F (2018) Jointly sparse hashing for image retrieval. IEEE Trans Image Process 27(12):6147–6158
Lei Z, Pietikainen M, Li SZ (2014) Learning discriminant face descriptor. IEEE Trans Pattern Anal Mach 36(2):289–302
Deng W, Hu J, Guo J (2017) Face recognition via collaborative representation: its discriminant nature and superposed representation. IEEE Trans Pattern Anal Mach 40(10):2513–2521
Kan M, Shan S, Zhang H, Lao S, Chen X (2016) Multi-view discriminant analysis. IEEE Trans Pattern Anal Mach 38(1):188–192
Guo M, Yang S, Nie F, Li X (2018) Locality-based discriminant feature selection with trace ratio. In: 25th IEEE international conference on image processing (ICIP ), pp 3337–3377
Zhang C, Liu Y, Hu Q, Liu X, Zhu P (2018) FISH-MML: fisher-HSIC multi-view metric learning. In: Proceedings of the twenty-seventh international joint conference on artificial intelligence (IJCAI), pp 3054–3060
Roweis S (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326
Cai D, Chen X (2017) Unsupervised large graph embedding. In: Proceeding of the Thirty-First AAAI conference on artificial intelligence, pp 2422–2428
Wen Z, Yin W (2013) A feasible method for optimization with orthogonality constraints. Math Program 142(1):397–434
Ding C, He X, Simon H (2005) On the equivalence of nonnegative matrix factorization and spectral clustering. In: Industrial conference on data mining (ICDM), pp 606–610
Yin Y, Liu L, Sun X (2011) Sdumla-hmt: a multimodal biometric database. In: Chinese conference on biometric recognition (CCBR), pp 260–268
Meng X, Yang G, Yin Y, Xiao R (2012) Finger vein recognition based on local directional code. Sensors 12:14937–14952
Acknowledgements
The authors would particularly like to thank the anonymous reviewers for their helpful suggestion. This work was supported in part by the NSFC-Xinjiang Joint Fund under Grant U1903127 and in part by the Key Research and Development Project of Shandong Province under Grants 2018GGX101032 and 2019GGX101056.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, H., Yang, G. & Yin, Y. Category-preserving binary feature learning and binary codebook learning for finger vein recognition. Int. J. Mach. Learn. & Cyber. 11, 2573–2586 (2020). https://doi.org/10.1007/s13042-020-01143-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-020-01143-1