|
|
Non-negative locality-constrained vocabulary tree for finger vein image retrieval |
Kun SU1,2, Gongping YANG1(), Lu YANG3, Peng SU4, Yilong YIN1,3 |
1. School of Computer Science and Technology, Shandong University, Jinan 250101, China 2. School of Mechanical, Electrical and Information Engineering, Shandong University (Weihai), Weihai 264209, China 3. School of Computer Science and Technology, Shandong University of Finance and Economics, Jinan 250014, China 4. School of Mathematics, Dali University, Dali 671000, China |
|
|
Abstract Finger vein image retrieval is a biometric identification technology that has recently attracted a lot of attention. It has the potential to reduce the search space and has attracted a considerable amount of research effort recently. It is a challenging problem owing to the large number of images in biometric databases and the lack of efficient retrieval schemes. We apply a hierarchical vocabulary tree modelbased image retrieval approach because of its good scalability and high efficiency.However, there is a large accumulative quantization error in the vocabulary tree (VT)model thatmay degrade the retrieval precision. To solve this problem, we improve the vector quantization coding in the VT model by introducing a non-negative locality-constrained constraint: the non-negative locality-constrained vocabulary tree-based image retrieval model. The proposed method can effectively improve coding performance and the discriminative power of local features. Extensive experiments on a large fused finger vein database demonstrate the superiority of our encoding method. Experimental results also show that our retrieval strategy achieves better performance than other state-of-theart methods, while maintaining low time complexity.
|
Keywords
non-negative locality-constrained vocabulary tree
finger vein image retrieval
large scale
inverted indexing
|
Corresponding Author(s):
Gongping YANG
|
Just Accepted Date: 28 March 2017
Online First Date: 02 April 2018
Issue Date: 08 April 2019
|
|
1 |
AKumar, YZhou. Human identification using finger images. IEEE Transactions on Image Processing, 2012, 21(4): 2228–2244
https://doi.org/10.1109/TIP.2011.2171697
|
2 |
LDong, GYang, YYin, F Liu, XXi. Finger vein verification based on a personalized best patches map. In: Proceedings of IEEE International Joint Conference on Biometrics. 2014, 1–8
https://doi.org/10.1109/BTAS.2014.6996234
|
3 |
FLiu, GYang, YYin, S Wang. Singular value decomposition based minutiae matching method for finger vein recognition. Neurocomputing, 2014, 145(145): 75–89
https://doi.org/10.1016/j.neucom.2014.05.069
|
4 |
GYang, XXi, YYin. Finger vein recognition based on (2D)2 PCA and metric learning. Journal of Biomedicine and Biotechnology, 2012, 2012(3): 324249
|
5 |
PPrabhakar, TThomas. Finger vein identification based on minutiae feature extraction with spurious minutiae removal. In: Proceedings of the 3rd International Conference on Advances in Computing and Communications. 2013, 196–199
https://doi.org/10.1109/ICACC.2013.45
|
6 |
WSong, TKim, H CKim, J H Choi, H JKong, S RLee. A finger-vein verification system using mean curvature. Pattern Recognition Letters, 2011, 32(11): 1541–1547
https://doi.org/10.1016/j.patrec.2011.04.021
|
7 |
BRosdi, CShing, SSuandi. Finger vein recognition using local line binary pattern. Sensors, 2011, 11(12): 11357–11371
https://doi.org/10.3390/s111211357
|
8 |
GYang, XXi, YYin. Finger vein recognition based on a personalized best bit map. Sensors, 2012, 12(2): 1738–1757
https://doi.org/10.3390/s120201738
|
9 |
FLiu, YYin, GYang, L Dong, XXi. Finger vein recognition with superpixel-based features. In: Proceedings of IEEE International Joint Conference on Biometrics. 2014, 1–8
https://doi.org/10.1109/BTAS.2014.6996232
|
10 |
EHenry. Classification and Uses of Finger Prints. London: Routledge,1900
|
11 |
RRaghavendra, J Surbiryala, CBusch. An efficient finger vein indexing scheme based on unsupervised clustering. In: Proceedings of IEEE International Conference on Identity, Security and Behavior Analysis. 2015, 1–8
https://doi.org/10.1109/ISBA.2015.7126343
|
12 |
JSurbiryala, R Raghavendra, CBusch. Finger vein indexing based on binary features. In: Proceedings of IEEE Colour and Visual Computing Symposium. 2015, 1–6
https://doi.org/10.1109/CVCS.2015.7274884
|
13 |
RZhang, ZZhang. A clustering based approach to efficient image retrieval. In: Proceedings of IEEE International Conference on Tools with Artificial Intelligence. 2002, 339–346
|
14 |
KLee, WStreet. Cluster-driven refinement for content-based digital image retrieval. IEEE Transactions on Multimedia, 2004, 6(6): 817–827
https://doi.org/10.1109/TMM.2004.837235
|
15 |
DTan, JYang, YShi, C Xu. A hierarchal framework for finger-vein image classification. In: Proceedings of Asian Conference on Pattern Recognition. 2013, 833–837
https://doi.org/10.1109/ACPR.2013.151
|
16 |
DMaltoni, DMaio, A KJain, S Prabhakar. Handbook of Fingerprint Recognition. Springer, 2009
https://doi.org/10.1007/978-1-84882-254-2
|
17 |
DTang, BHuang, RLi, WLi. A person retrieval solution using finger vein patterns. In: Proceedings of International Conference on Pattern Recognition. 2010, 1306–1309
https://doi.org/10.1109/ICPR.2010.325
|
18 |
KWang, LYang, KSu , G Yang, YYin. Binary search path of vocabulary tree based finger vein image retrieval. In: Proceedings of International Conference of Biometrics. 2016
|
19 |
RArandjelovic, A Zisserman. Three things everyone should know to improve object retrieval. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2012, 2911–2918
https://doi.org/10.1109/CVPR.2012.6248018
|
20 |
JPhilbin, OChum, MIsard, J Sivic, AZisserman. Object retrieval with large vocabularies and fast spatial matching. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2007, 1–8
https://doi.org/10.1109/CVPR.2007.383172
|
21 |
MYang, DZhang, XFeng, D Zhang. Fisher discrimination dictionary learning for sparse representation. In: Proceedings of International Conference on Computer Vision. 2011, 543–550
https://doi.org/10.1109/ICCV.2011.6126286
|
22 |
DNister, H Stewenius. Scalable recognition with a vocabulary tree. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2006, 2161–2168
https://doi.org/10.1109/CVPR.2006.264
|
23 |
ZSun, HZhang, TTan, J Wang. Iris image classification based on hierarchical visual codebook. IEEE Transactions on Software Engineering, 2014, 36(6): 1120–1133
https://doi.org/10.1109/TPAMI.2013.234
|
24 |
JWang, JYang, KYu, FLv, g THuan, Y Gong. Locality-constrained linear coding for image classification. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2010, 3360–3367
https://doi.org/10.1109/CVPR.2010.5540018
|
25 |
D DLee, H SSeung. Learning the parts of objects by non-negative matrix factorization. Nature, 1999, 401(6755): 788–791
https://doi.org/10.1038/44565
|
26 |
D DLee, H SSeung. Algorithms for non-negative matrix factorization. In: Proceedings of the 13th International Conference on Neural Information Processing Systems. 2000, 535–541
|
27 |
WXu, XLiu, YGong. Document clustering based on non-negative matrix factorization. In: Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval. 2003, 267–273
https://doi.org/10.1145/860435.860485
|
28 |
ZLi, JLiu, YYang, X Zhou, HLu. Clustering-guided sparse structural learning for unsupervised feature selection. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(9): 2138–2150
https://doi.org/10.1109/TKDE.2013.65
|
29 |
ZLi, JLiu, JTang, H Lu. Robust structured subspace learning for data representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(10): 2085–2098
https://doi.org/10.1109/TPAMI.2015.2400461
|
30 |
YChen, XGuo. Learning non-negative locality-constrained linear coding for human action recognition. In: Proceedings of Visual Communications and Image Processing. 2013, 1–6
https://doi.org/10.1109/VCIP.2013.6706432
|
31 |
P OHoyer. Non-negative sparse coding. In: Proceedings of IEEE Workshop on Neural Networks for Signal Processing. 2002, 557–565
https://doi.org/10.1109/NNSP.2002.1030067
|
32 |
T HLin, H TKung. Stable and efficient representation learning with nonnegativity constraints. In: Proceedings of the 31st International Conference on Machine Learning. 2014, 1323–1331
|
33 |
CBao, LHe, YWang. Linear spatial pyramid matching using nonconvex and non-negative sparse coding for image classification. In: Proceedings of IEEE China Summit and International Conference on Signal and Information Processing. 2015, 186–190
|
34 |
GLiu, YLiu, M ZGuo, P N Liu, C YWang. Non-negative localityconstrained linear coding for image classification. Acta Automatica Sinica, 2015, 41(7): 1235–1243
|
35 |
XWang, MYang , TCour, S Zhu. Contextual weighting for vocabulary tree based image retrieval. In: Proceedings of International Conference on Computer Vision. 2011, 209–216
|
36 |
LYang, GYang, YYin, R Xiao. Sliding window-based region of interest extraction for finger vein images. Sensors, 2013, 13(3): 3799–3815
https://doi.org/10.3390/s130303799
|
37 |
OTimo, M Pietikainen, TMaenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971–987
https://doi.org/10.1109/TPAMI.2002.1017623
|
38 |
RJain, R Kasturi, B GSchunck. Machine Vision. New York: McGraw- Hill, 1995
|
39 |
DLowe. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 2004, 60(2): 91–110
https://doi.org/10.1023/B:VISI.0000029664.99615.94
|
40 |
LZheng, SWang, ZLiu, Q Tian. Lp-norm IDF for large scale image search. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2013, 1626–1633
https://doi.org/10.1109/CVPR.2013.213
|
41 |
JSivic, A Zisserman. Video google: a text retrieval approach to object matching in videos. In: Proceedings of IEEE International Conference on Computer Vision. 2003, 1470
https://doi.org/10.1109/ICCV.2003.1238663
|
42 |
D MChen, S STsai, VChandrasekhar, GTakacs, R Vedantham, RGrzeszczuk, BGirod. Inverted index compression for scalable image matching. In: Proceedings of IEEE Data Compression Conference. 2010, 525
https://doi.org/10.1109/DCC.2010.53
|
43 |
YYin, LLiu, XSun. SDUMLA-HMT: a multimodal biometric database. In: Sun Z, Lai J, Chen X, et al, eds. Biometric Recognition, Springer Berlin Heidelberg, 2011, 260–268
https://doi.org/10.1007/978-3-642-25449-9_33
|
44 |
YLu, S JXie, SYoon, Z Wang, S PDong. An available database for the research of finger vein recognition. In: Proceedings of International Congress on Image and Signal Processing. 2013, 410–415
https://doi.org/10.1109/CISP.2013.6744030
|
45 |
YLu, S JXie, SYoon, J Yang, D SPark. Robust finger vein roi localization based on flexible segmentation. Sensors, 2013, 13(11): 14339–14366
https://doi.org/10.3390/s131114339
|
46 |
MAsaari, S ASuandi, B ARosdi. Fusion of band limited phase only correlation and width centroid contour distance for finger based biometrics. Expert Systems with Applications, 2014, 41(7): 3367–3382
https://doi.org/10.1016/j.eswa.2013.11.033
|
47 |
YAvrithis, GTolias. Hough pyramid matching: speeded-up geometry re-ranking for large scale image retrieval. International Journal of Computer Vision, 2014, 107(1): 1–19
https://doi.org/10.1007/s11263-013-0659-3
|
48 |
KHe, FWen, JSun. K-means hashing: an affinity-preserving quantization method for learning binary compact codes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition. 2013, 2938–2945
https://doi.org/10.1109/CVPR.2013.378
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|