(47-3) 12 * << * >> * Russian * English * Content * All Issues

Using a lightweight Siamese neural network for generating a feature vector in a vascular authentication system
D.E. Prozorov 1, A.V. Zemtsov 1

Vyatka State University, 610000, Kirov, Russia, Moskovskaya 36

 PDF, 925 kB

DOI: 10.18287/2412-6179-CO-1204

Pages: 433-441.

Full text of article: Russian language.

Abstract:
The article analyzes the possibility of using a Siamese convolutional neural network to solve the problem of vascular authentication on an embedded hardware platform with limited computing resources (Orange Pi One). The authors give a brief review of modern methods for calculating image feature vectors used in the tasks of classifying, comparing or searching for images by content: based on variational series (histograms), local descriptors, singular point descriptors, descriptors based on hash functions, neural network descriptors. They suggest using the architecture of a biometric authentication system (BAS) based on images of palms in the visible and near-IR spectra based on a Siamese convolutional neural network. The developed software solution allows using the Siamese neural network in the "full network" (both symmetrical channels of the neural network are used) and "half of the neural network" (only one channel is used) modes to reduce the time for comparing biometric data vectors - images of the palms of registered BAS users. The authors demonstrate advantages of the neural network features: universality, scalability and competitiveness, including on embedded hardware and software solutions with limited computing resources without graphics accelerators. The studies have shown that using the Siamese neural network, the "overall accuracy" of palm image classification can be improved from 0.929 to 0.968 when compared with the image vectorization method based on a perceptual hash, while showing a comparable authentication time for individuals registered in BAS. In the experiments, the authors use a database of 2,000 images for 400 people.

Keywords:
biometric authentication, image processing, image descriptors, artificial neural network, Siamese neural network.

Citation:
Prozorov DE, Zemtsov AV. Using a lightweight Siamese neural network for generating a feature vector in a vascular authentication system. Computer Optics 2023; 47(3): 433-441. DOI: 10.18287/2412-6179-CO-1204.

References:

  1. Mcconnell RK. Method of and apparatus for pattern recognition. US Patent 4,567,610 of June 28, 1986.
  2. Freeman WT, Roth M. Orientation histograms for hand gesture recognition. Int Workshop on Automatic Face- and Gesture-Recognition, MERL-TR94-031995: 296-301.
  3. Bosch A, Zisserman A. Pyramid histogram of oriented gradients (PHOG). 2022. Source: <https://www.robots.ox.ac.uk/~vgg/research/caltech/phog.html>.
  4. Ojala T, Pietikainen M, Harwood D. Performance evaluation of texture measures with classification based on Kullback discrimination of distributions. Proc 12th Int Conf on Pattern Recognition 1994: 582-585. DOI: 10.1109/ICPR.1994.576366.
  5. Gengjian X, Li S, Jun S, Meng W. Hybrid center-symmetric local pattern for dynamic background subtraction. IEEE Int Conf on Multimedia and Expo 2011: 1-6. DOI: 10.1109/ICME.2011.6011859.
  6. Gupta R, Patil H, Mittal A. Robust order-based methods for feature description. IEEE Computer Society Conf on Computer Vision and Pattern Recognition 2010: 334-341. DOI: 10.1109/CVPR.2010.5540195.
  7. Silva C, Bouwmans T, Frelicot C. An eXtended center-symmetric local binary pattern for background modeling and subtraction in videos. VISAPP 2015 – 10th Int Conf on Computer Vision Theory and Applications 2015: 395-402. DOI: 10.5220/0005266303950402.
  8. Wu X, Sun J. An extended center-symmetric local ternary patterns for image retrieval. In Book: Lin S, Huang X, eds. Advances in computer science, environment, ecoinformatics, and education. Berlin, Heidelberg: Springer-Verlag; 2011: 359-364. DOI: 10.1007/978-3-642-23321-0_56.
  9. Ferraz CT, Pereira O, Gonzaga A. Feature description based on center-symmetric local mapped patterns. Proc ACM Symposium on Applied Computing 2014: 39-44. DOI: 10.1145/2554850.2554895.
  10. Narayanan V, Parsi B. Center symmetric local descriptors for image classification. Int J Nat Comput Res 2018; 7(4): 56-70. DOI: 10.4018/IJNCR.2018100104.
  11. Datta R, Joshi D, Li J, Wang J. Image retrieval: Ideas, influences, and trends of the new age. ACM Comput Surv 2008; 40(2): 5. DOI: 10.1145/1348246.1348248.
  12. Chatzichristofis SA, Boutalis YS. FCTH: Fuzzy color and texture histogram-a low level feature for accurate image retrieval. 9th Int Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS) 2008: 191-196. DOI: 10.1109/WIAMIS.2008.24.
  13. Zagoris K, Chatzichristofis SA, Papamarkos N, Boutalis YS. Automatic image annotation and retrieval using the joint composite descriptor. 14th Panhellenic Conf on Informatics 2010: 143-147. DOI: 10.1109/PCI.2010.38.
  14. David GL. Distinctive image features from scale-invariant keypoints. Int J Comput Vis 2004; 60(2): 91-110. DOI: 10.1023/B:VISI.0000029664.99615.94.
  15. Bay H, Tuytelaars T, Van GL. SURF: Speeded up robust features. In Book: Leonardis A, Bischof H, Pinz A, eds. Computer vision -- ECCV 2006. Berlin, Heidelberg: Springer-Verlag; 2006: 404-417. DOI: 10.1007/11744023_32.
  16. Ke Y, Sukthankar R. PCA-SIFT: a more distinctive representation for local image descriptors. 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2004: II-II. DOI: 10.1109/CVPR.2004.1315206.
  17. Mikolajczyk K, Schmid C. A performance evaluation of local descriptors. IEEE Trans Pattern Anal Mach Intell 2005; 27(10): 1615-1630. DOI: 10.1109/TPAMI.2005.188.
  18. Calonder M., Lepetit V, Strecha C, Fua P. BRIEF: Binary robust independent elementary features. In Book: Daniilidis K, Maragos P, Paragios N, eds. Computer vision -- ECCV 2010. Berlin, Heidelberg: Springer-Verlag; 2010: 778-792. DOI: 10.1007/978-3-642-15561-1_56.
  19. Rublee E, Rabaud V, Konolige K, Bradski G. ORB: An efficient alternative to SIFT or SURF. 2011 Int Conf on Computer Vision 2011: 2564-2571. DOI: 10.1109/ICCV.2011.6126544.
  20. Alcantarilla PF, Nuevo J, Bartoli A. Fast explicit diffusion for accelerated features in nonlinear scale spaces. BMVC 2013 – Electronic Proceedings of the British Machine Vision Conference 2013: 13.1-13.11. DOI: 10.5244/C.27.13.
  21. Leutenegger S, Chli M, Siegwart RY. BRISK: Binary Robust invariant scalable keypoints. 2011 Int Conf on Computer Vision 2011: 2548-2555. DOI: 10.1109/ICCV.2011.6126542.
  22. Tareen SAK, Saleem Z. A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK. 2018 Int Conf on Computing, Mathematics and Engineering Technologies (iCoMET) 2018: 1-10. DOI: 10.1109/ICOMET.2018.8346440.
  23. Zauner C. Implementation and benchmarking of perceptual image hash functions. Master’s Thesis, Upper Austria University of Applied 2010.
  24. pHash. The open source perceptual hash library. 2022. Source: <http://www.phash.org>.
  25. ImageHash. 2022. Source: <https://github.com/JohannesBuchner/imagehash>.
  26. Sivic J, Zisserman A. Video google: A text retrieval approach to object matching in videos. Int Conf on Computer Vision 2003: 1470-1477. DOI: 10.1109/iccv.2003.1238663.
  27. Bromley J, Guyon I, LeCun Y, Säckinger E, Shah R. Signature verification using a "Siamese" time delay neural network. Adv Neural Inf Process Syst 1993; 07(04). DOI: 10.1142/s0218001493000339.
  28. Hadsell R, Chopra S, LeCun Y. Dimensionality reduction by learning an invariant mapping. 2006 IEEE Computer Society Conf on Computer Vision and Pattern Recognition (CVPR'06) 2006: 1735-1742. DOI: 10.1109/CVPR.2006.100.
  29. Note on CASIA Palmprint Database. 2022. Source: <http://www.cbsr.ia.ac.cn/english/Palmprint%20Databases.asp>.
  30. Zhang L, Cheng Z, Shen Y, Wang D. Palmprint and palmvein recognition based on DCNN and a new large-scale contactless palmvein dataset. Symmetry 2018; 10(4): 78. DOI: 10.3390/sym10040078.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20