Application of a convolutional neural networks for images recognition

  • № 2(92) 2020

Страницы: 

69

 – 

81

Язык: английский

Открыть файл статьи
Открыть страницу статьи в Интернет

Аннотация

В задачах распознавания изображений используются различные подходы, когда изображение зашумлено и имеется малая выборка наблюдений. В статье рассматриваются непараметрические методы распознавания и методы, основанные на сверточных нейронных сетях. Этот тип нейронных сетей позволяет сворачивать изображения, проводить субдискретизацию необходимое число раз. Причем скорость распознавания изображения достаточно высокая, а размерность данных понижается использованием сверточных слоев. Одним из важнейших элементов применения свёрточных нейронных сетей является обучение.

Тасвирни таниб олиш муаммоларида, расм шовқинли бўлганда ва кичик кузатишлар намунаси мавжуд бўлганда, турли хил ёндашувлар қўлланилади. Мақолада параметрик бўлмаган аниқлаш усуллари ва конвулсион нейрон тармоқларига асосланган усуллар муҳокама қилинади. Ушбу турдаги нейрон тармоқ сизга тасвирларни сиқиб чиқаришга, зарур бўлганда схемаларни қисқартиришга имкон беради. Бундан ташқари, расмни аниқлаш тезлиги жуда юқори ва конвулсион қатламлардан фойдаланган ҳолда маълумотлар ҳажми камаяди. Конвулсион нейрон тармоқларни қўллашнинг энг муҳим элементларидан бири бу машғулотдир.

In the problems of image recognition, various approaches used when the image is noisy and there is a small sample of observations. The paper discusses nonparametric recognition methods and methods based on deep neural networks. This neural network allows you to collapse images, to perform downsampling as many times as necessary. Moreover, the image recognition speed is quite high, and the data dimension is reduced by using convolutional layers. One of the most important elements of the application of convolutional neural networks is training. The article gives the results of work on the application of convolutional neural networks. The work was carried out in several stages. In the first stage was carried out the modeling of the convolutional neural network and was developed its architecture. In the second stage, the neural network was trained. The third phase produced Python software. The software health check and video processing speed were then performed.

Список использованных источников

  1. Duda R., Hart P. Pattern recognition and scene analysis. Translation from English. G. G. Vajeshtejnv, A. M. Vaskovski, edited by V. L. Stefanyuk, “MIR” Publishing House, Moskow 1976. – 509 p.
  2. Mokeev V.V., Tomilov S.V. On the solution of the problem of small sample size when using linear discriminant analysis in face recognition problems // Business Informatics. – 2013. №1(23). – pp. 37-43.
  3. Lapko A.V., Chencov S.V., Lapko V.A. Non-parametric patterns of pattern recognition in small samples // Autometry. -1999. -№6. – pp. 105-113.
  4. Authorized translation from the English language edition, entitled DIGITAL IMAGE PROCESSING: International Version 3rd Edition; ISBN 0132345633, by GONZALEZ, RAFAEL C; WOODS, RICHARD E., published by Pearson Education, Inc,publishing as Prentice Hall. Copyright ©2008 by Pearson Education, Inc.
  5. Voronin, V.V. Methods and algorithms of image recovery in conditions of incomplete a priori information: monograph/V.V.Voronin, V.I.Marchuk - Shakhts: VPO "JURGUES," 2010. – 89 p.
  6. Tan, X. Face recognition from a single image per person: a survey / X. Tan, S. Chen, Z.H. Zhou, F. Zhang // Pattern Recognition. – 2006. – Vol. 39, Issue 9. – pp. 1725-1745. – DOI: 10.1016/j.patcog. 2006.03.013.
  7. Bertinetto, L. Learning feed-forward one-shot learners / L. Bertinetto, J.F. Henriques, J. Valmadre, P. Torr, A. Vedaldi // Advances in Neural Information Processing Systems 29: Annual Conference on Neural Information Processing Systems 2016. – 2016. – pp. 523-531.
  8. Parkhi, O.M. Deep face recognition / O.M. Parkhi, A. Vedaldi, A. Zisserman // Proceedings of the British Machine Vision. – 2015. – pp. 6-17.
  9. Russakovsky O, Deng J, Su H, Krause J, Satheesh S, MaS, 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.
  10. Lempitsky V. Convolutional neural network. Available at: [https://postnauka.ru/ video/66872].
  11. Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol Cybern. 1980;36:193–202. doi: 10.1007/BF00344251. [CrossRef] [Google Scholar].
  12. Hubel DH, Wiesel TN. Receptive fields and functional architecture of monkey striate cortex. J Physiol. 1968;195:215–243. doi: 10.1113/jphysiol.1968.sp008455. [CrossRef] [Google Scholar].
  13. Russell Stewart, Norvig Peter. Artificial Intelligence: A Modern Approach, 2nd ed.: Transl. From English. –M .: Williams Publishing House, 2006. – 1408p.
  14. Qian N. On the momentum term in gradient descent learning algorithms. Neural Netw. 1999;12:145–151. doi: 10.1016/S0893-6080(98)00116-6. [PubMed] [CrossRef] [Google Scholar].
  15. Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv. Available online at: https://arxiv.org/pdf/1412.6980.pdf. Accessed 23 Jan 2018.
  16. Ruder S (2016) An overview of gradient descent optimization algorithms. arXiv. Available online at: https://arxiv.org/pdf/1609.04747.pdf. Accessed 23 Jan 2018.
  17. Yoshua Bengio, Y. Le Cun, and D. Henderson. Globally trained handwritten word recognizer using spatial representation, space displacement neural networks and hidden Markov models. In Advances in Neural Information Processing Systems 6, San Mateo CA, 1994. Morgan Kaufmann.
  18. Convolutional neural networks: an overview and application in radiology. Rikiya Yamashita, Mizuho Nishio, Richard Kinh Gian Do, Kaori Togashi. Insights Imaging. 2018 Aug; 9(4): 611–629. Published online 2018 Jun 22. doi: 10.1007/s13244-018-0639-9. Available online at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6108980/.
  19. Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): maintaining and operating a public information repository. J Digit Imaging. 2013;26:1045–1057. doi: 10.1007/s10278-013-9622-7. [PMC free article] [PubMed] [CrossRef] [Google Scholar].
  20. Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers RM (2017) ChestX-ray8: hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp 3462–3471. 10.1109/CVPR.2017.369.
  21. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539. [PubMed] [CrossRef] [Google Scholar].
  22. Marakhimov, Avazjon and Khudaybergenov, Kabul (2019) "Convergence analysis of feedforward neural networks with backpropagation," Bulletin of National University of Uzbekistan: Mathematics and Natural Sciences: Vol. 2 : Iss. 2, Article 1. Available at: https://uzjournals.edu.uz/mns_nuu/vol2/iss2/1.
  23. Tomasi C., Manduchi R. Bilateral filtering for gray and color images // Proc. IEEE Int. Conf. Computer Vision, 1998, –pp. 839-846.
  24. Overton K., Weymouth T. A noise reducing preprocessing algorithm // Proc. IEEE Computer Science Conf. Pattern Recognition and Image Processing, Chicago, IL, 1979, –pp. 498-507.
  25. C. Chui and Chen Guanrong. Kalman Filtering with Real-Time Applications. Fifth edition (e-Book). Springer Series in Information Sciences. 2017, – 245 P.
  26. Marakhimov A.R., Varlamova L.P. Block Form of Kalman Filter in Processing Images with Low Resolution// Chemical Technology. Control and Management/ -2019, №3. Рр.57-72.
  27. Marakhimov, Avazjon and Khudaybergenov, Kabul (2018) "Neuro-fuzzy identification of nonlinear dependencies,"Bulletin of National University of Uzbekistan: Mathematics and Natural Sciences: Vol. 1 : Iss. 3, Article 1. Available at: https://uzjournals.edu. uz/mns_nuu/vol1/iss3/1.
  28. Varlamova L.P., Salakhova K.N., Tillakhodzhaeva R.S., Neural network approach in the task of data processing.// Young scientist No. 202, 2018. Part 1, –pp. 99-101.
  29. Marakhimov A.R., Khudaybergenov K.K., “A fuzzy MLP approach for identification of nonlinear systems”, Contemporary problems in mathematics and physics, CMFD, 65, no. 1, Peoples' Friendship University of Russia, M., 2019, –pp 44–53.
  30. Jason Brownlee. A Gentle Introduction to Transfer Learning for Deep Learning.//Available at: [https://machinelearningmastery.com/transfer-learning-for-deep-learning/].
  31. Lee DH (2013) Pseudo-label: the simple and efficient semi-supervised learning method for deep neural networks. In: Proceedings of the ICML 2013 Workshop: Challenges in Representation Learning. Available online at: http://deeplearning.net/wp-content/uploads/ 2013/ 03/pseudo_label_final.pdf. Accessed 23 Jan 2018.
  32. https://pythonhosted.org/nolearn/lasagne.html.
  33. He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10.1109/CVPR.2016.90.
  34. Szegedy C, Liu W, Jia Y et al (2015) Going deeper with convolutions. In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10.1109/CVPR.2015.7298594.
  35. Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 10.1109/CVPR.2017.243.
  36. Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: Proceedings of Computer Vision – ECCV 2014, vol 8689. – pp 818–833.
  37. Yosinski J, Clune J, Bengio Y, Lipson H (2014) How transferable are features in deep neural networks? arXiv. Available online at: https://arxiv.org/pdf/1411.1792.pdf. Accessed 25 Jan 2018.

Список всех публикаций, цитирующих данную статью