ATTENTION! SITE "MOVED" TO A NEW ADDRESS:
http://journals.knute.edu.ua/foreign-trade

  FREE FULL TEXT (PDF) 

UDC 004.94=111   DOI: https://doi.org/10.31617/zt.knute.2019(104)07
KRYVORUCHKO Olena,
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
ORCID: 0000-0002-7661-9227		   DSc (Engineering), Professor, Head of Department of Software Engineering
and Cyber Security of Kyiv National University of Trade and Economics
19, Kyoto str., Kyiv, 02156, Ukraine
     
KHOROLSKA Karyna,
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
ORCID: 0000-0003-3270-4494		   Server-side Developer,
Softorino Inc. 
Huntington Beach, California, USA
     
CHUBAIEVSKYI Vitalii,
E-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
ORCID:0000-0001-8078-2652		   PhD (Political Sciences), Associate Professor of Department of Software Engineering
and Cyber Security of Kyiv National University of Trade and Economics
19, Kyoto str., Kyiv, 02156, Ukraine
 
USAGE OF NEURAL NETWORKS IN IMAGE RECOGNITION 

This article focuses on the operation of the classification of blueprint parts. Classification characteristic is the main part of the designation of the part or product and their design documents, solving a number of topical tasks from creation of a single information language for automated systems to unification and standardization.

Keywords: neural network, object recognition, classification, domains.

REFERENCES 

  1. Alexandre, L. A. (2016). 3D Object Recognition Using Convolutional Neural Networks with Transfer Learning Between Input Channels. In: Menegatti E., Michael N., Berns K., Yamaguchi H. (Eds). Intelligent Autonomous Systems 13. Advances in Intelligent Systems and Computing. (vol. 302). Springer, Cham. DOI: https://doi.org/10.1007/978-3-319-08338-4_64 [in English].
  2. Andre, Esteva, & Brett, Kuprel (2017).Dermatologist-level classification of skin cancer with deep neural networks. (Vol. 542), (pp. 115–118). 02 February. Retrieved from https://www.nature.com/articles/nature21056?TB_iframe=true&width=914.4&height=921.6. DOI: https://doi.org/10.1038/nature21056 [in English].
  3. Popescu, A. C., & Farid, H. (2005). Exposing digital forgeries by detecting traces of resampling. IEEE Transactions on signal processing. (Vol. 53), 2, (pp. 758-767). DOI: https://doi.org/10.1109/TSP.2004.839932 [in English].
  4. Qian, Y., Dong, J., Wang, W., & Tan, T. (2015). Deep learning for steganalysis via convolutional neural networks. Media Watermarking, Security and Forensics. (Vol. 9409), (pp. 94 090J). DOI: https://doi.org/10.1117/12.2083479 [in English].
  5. Lin, M., Chen, Q., & Yan, S. (2014). Network in network, in International Conference on Learning Representations [in English].
  6. Ciresan, D. C., Meier, U. J., Masci, Gambardella L. M., & Schmidhuber J. (2011). High-performance neural networks for visual object classification. Arxiv preprint arXiv:1102.0183 [in English].
  7. Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks, in Advances in neural information processing systems, (pp. 1097-1105) [in English].