Maximum-likelihood dissimilarities in image recognition with deep neural networks
A.V. Savchenko

 

National Research University Higher School of Economics, Nizhny Novgorod, Russia

Full text of article: Russian language.

 PDF

Abstract:
In this paper we focus on the image recognition problem in the case of a small sample size based on the nearest neighbor rule and matching high-dimensional feature vectors extracted with a deep convolutional neural network. We propose a novel recognition algorithm based on the maximum likelihood method for the joint density of dissimilarities between the observed image and available instances in a training set. This likelihood is estimated using the known asymptotically normally distribution of the Jensen-Shannon divergence between image features, if the latter can be treated as probability density estimates. This asymptotic behavior is in agreement with the well-known experimental estimates of the distributions of dissimilarity distances between the high-dimensional vectors. The experimental study in unconstrained face recognition for the LFW (Labeled Faces in the Wild) and YTF (YouTube Faces) datasets demonstrated that the proposed approach makes it possible to increase the recognition accuracy by 1-5% when compared with conventional classifiers.

Keywords:
statistical pattern recognition, image processing, deep convolutional neural networks, maximum-likelihood directed enumeration method, unconstrained face identification.

Citation:
Savchenko AV. Maximum-likelihood dissimilarities in image recognition with deep neural networks. Computer Optics 2017; 41(3): 422-430. DOI: 10.18287/2412-6179-2017-41-3-422-430.

References:

  1. LeCun Y, Bengio Y, Hinton G. Deep learning, Nature 2015; 521(7553): 436-444. DOI: 10.1038/nature14539.
  2. Prince SJ. Computer vision: models, learning, and inference. New York: Cambridge University Press; 2012. ISBN: 978-1-107-01179-3.
  3. Goodfellow I, Bengio Y, Courville A. Deep learning (Adap­tive computation and machine learning series). Cambridge, London: MIT Press; 2016. ISBN: 978-0-262-03561-3.
  4. Savchenko AV. Search techniques in intelligent classifica­tion systems. Switzerland: Springer International Publi­shing; 2016. ISBN 978-3-319-30513-4.
  5. Zhao Y, Liu Y, Zhong S, Hua KA. Face recognition from a single registered image for conference socializing, Expert Systems with Applications 2015; 42(3): 973-979. DOI: 10.1016/j.eswa.2014.08.016.
  6. Raudys SJ, Jain AK. Small sample size effects in statistical pattern recognition: Recommendations for practitioners. IEEE Transactions on Pattern Analysis and Machine Intelligence 1991, 13(3): 252-264. DOI: 10.1109/34.75512.
  7. Mokeev VV, Tomilov SV. On solution of the small sample size problem with linear discriminant analysis in face recognition [In Russian]. Business-Informatics 2013; 1(23): 37-43.
  8. Fursov VA, Minayev EYu. Creation of support subspaces in the fractal image recognition tasks [In Russian]. Proceedings of International Conference on Information Technology and Nanotechnology (ITNT) 2016: 530-537.
  9. Fursov VA. Adaptive identification on small number of observations [In Russian]. Information technologies (Appendix) 2013; 9: 1-32.
  10. Lapko AV, Lapko VA, Chentsov SV. Nonparametric models of pattern recognition under conditions of small samples. Optoelectronics, Instrumentation and Data Processing 1999; 6: 83-90.
  11. Savchenko VV. Decision of a small samples problem on the basis of the information theory of speech perception [In Russian]. Proceedings of the Russian Universities: Radio­electronics 2008; 5: 33-44.
  12. Tan X, Chen S, Zhou ZH, Zhang F. Face recognition from a single image per person: a survey. Pattern Recognition 2006; 39(9): 1725-1745. DOI: 10.1016/j.patcog.2006.03.013.
  13. Bertinetto L, Henriques JF, Valmadre J, Torr P, Vedaldi A. Learning feed-forward one-shot learners. Advances in Neural Information Processing Systems 29 (NIPS-2016) 2016: 523-531.
  14. Parkhi OM, Vedaldi A, Zisserman A. Deep face recogniti­on. Proceedings of the British Machine Vision 2015: 6-17.
  15. Liu J, Deng Y, Huang C. Targeting ultimate accuracy: Face recognition via deep embedding. arXiv preprint arXiv:1506.07310 2015.
  16. Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. Proceedings of the IEEE International Con­ference on Computer Vision and Pattern Recognition (CVPR) 2015: 1-9. DOI: 10.1109/CVPR.2015.7298594.
  17. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Li FF. Imagenet large scale visual recognition challenge. International Journal of Computer Vision 2015; 115(3): 211-252. DOI: 10.1007/s11263-015-0816-y.
  18. Taigman Y, Yang M, Ranzato M, Wolf L. DeepFace: Closing the gap to human-level performance in face verification. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2014: 1701-1708. DOI: 10.1109/CVPR.2014.220.
  19. Savchenko AV. Maximum-Likelihood Approximate Nearest Neighbor Method in Real-time Image Recognition, Pattern Recognition 2017; 61: 459-469. DOI: 10.1016/j.patcog.2016.08.015.
  20. Savchenko AV. The maximal likelihood enumeration method for the problem of classifying piecewise regular objects. Automation and Remote Control 2016; 77(3): 443-450. DOI: 10.1134/S0005117916030061.
  21. Savchenko AV, Belova NS. Statistical testing of segment homogeneity in classification of piecewise-regular objects, International Journal of Applied Mathematics and Computer Science 2015; 25(4): 915-925. DOI: 10.1515/amcs-2015-0065.
  22. Dalal N, Triggs B. Histograms of oriented gradients for human detection. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2005: 886-893. DOI: 10.1109/CVPR.2005.177.
  23. Lowe D. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision 2004; 60(2): 91-110. DOI: 10.1023/B:VISI.0000029664.99615.94.
  24. Ahonen T, Hadid A, Pietikainen M. Face recognition with local binary patterns. Proceedings of the European Conference on Computer Vision (ECCV 2004) 2004: 469-481. DOI: 10.1007/978-3-540-24670-1_36.
  25. Savchenko AV. Image recognition on the basis of probabilistic neural network with homogeneity testing [In Russian]. Computer Optics 2013; 37(2): 254-262.
  26. Kullback S. Information Theory and Statistics. Mineola, New York: Dover Publications, Inc.; 1997. ISBN: 978-0-486-69684-7.
  27. Burghouts GJ, Smeulders AWM, Geusebroek J-M. The distribution family of similarity distances. Proceedings of the 20th International Conference on Neural Information Processing Systems (NIPS’07) 2007: 201-208.
  28. Best-Rowden L, Han H, Otto C, Klare BF, Jain AK. Unconstrained face recognition: identifying a person of interest from a media collection. IEEE Transactions on Information Forensics and Security 2014; 9(12): 2144-2157. DOI: 10.1109/TIFS.2014.2359577.
  29. Wolf L, Hassner T, Maoz I. Face recognition in unconstrained videos with matched background similarity, Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2011: 529-534. DOI: 10.1109/CVPR.2011.5995566.
  30. Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Darrell T. Caffe: Convolutional architecture for fast feature embedding. Proceedings of the 22nd ACM International Conference on Multimedia (MM’14) 2014: 675-678. DOI: 10.1145/2647868.2654889.
  31. Wu X, He R, Sun Z. A lightened CNN for deep face representation. arXiv preprint arXiv:1511.02683v1 2015.
  32. Yi D, Lei Z, Liao S, Li SZ. Learning Face Representation from Scratch, arXiv preprint arXiv:1411.7923, 2014.
  33. Video-based face recognition software. Source: áhttps://git­hub.com/HSE-asavchenko/HSE_FaceRec/tree/master/src/caf­fe_modelsñ.
  34. Learned-Miller E, Huang GB, RoyChowdhury A, Li H, Hua G. Labeled faces in the wild: A survey. In book: Kawulok M, Celebi ME, Smolka B, eds. Advances in Face Detection and Facial Image Analysis. Springer International Publishing Switzerland; 2016: 189-248. DOI: 10.1007/978-3-319-25958-1_8.
  35. Wang H, Wang Y, Cao Y. Video-based face recognition: a survey. World Academy of Science. Engineering and Technologies 2009; 60: 293-302.
© 2009, IPSI RAS
Institution of Russian Academy of Sciences, Image Processing Systems Institute of RAS, Russia, 443001, Samara, Molodogvardeyskaya Street 151; E-mail: journal@computeroptics.ru; Phones: +7 (846) 332-56-22, Fax: +7 (846) 332-56-20