Abstract
The purpose is to develop an image hashing algorithm using convolutional neural networks. The proposed algorithm consists of three phases: (1) preliminary training the neural network on training data; (2) configuring the neural network for simultaneous training of the neural network to recognize semantic features and configuring the approximating hash-like function for computing hash codes; (3) retrieving images using the proposed hierarchical deep search algorithm.
Similar content being viewed by others
REFERENCES
GOST (State Standard) P 34.11-2012: Information technology. Cryptographic Information Security. Hashing Function, 2012.
Methodology for detecting information security threats in information systems, 2015. https://mindstep.ru/wiki/index.php/. Accessed September 26, 2021.
Protection against unauthorized information access: Terms and Definitions. Guidance Document of the Federal Service for Technical and Export Control (FSTEC), Russia, Moscow: Kremlin, 1992.
Ershov, A.V., Linear and Affine Spaces and Mappings, Moscow: Mosk. Fiz.-Tekhn Inst., 2016, [in Russian].
Emel’yanov, S.O., Methods of augmenting training samples, Sensor Systems, 2018, vol. 32, no.3.
Gorodetskii, S.Yu. and Grishagin, V.A., Nonlinear Programming and Multiextremum Optimization, Nizhnii Novgorod: Izd-vo Nizh. Univ., 2007, [in Russian].
Lowe, D., Object recognition from local scale-invariant features, 1999. https://doi.org/10.1109/ICCV.1999.790410. http://ieeexplore.ieee.org/document/790410. Accessed January 16, 2021.
Zhen, Zuo, Bing, Shuai, et al., Convolutional recurrent neural networks: Learning spatial dependencies for image representation, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVRPW), 2015. https://doi.org/10.1109/CVPRW.2015.7301268. http://ieeexplore.ieee.org/document/7301268. Accessed January 30, 2021.
Joe Yue-Hei Ng, J., Fan Yang, et al., Exploiting local features from deep networks for image retrieval, IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, 2015. https://doi.org/10.1109/CVPRW.2015.7301272. http://ieeexplore.ieee.org/document/7301272. Accessed January 30, 2021.
Alex X. Liu, A.X., Shen, K., and Torng, E., Large scale Hamming distance query processing, ICDE Conference, 2011, pp. 553–564.
Maire, M., Affinity CNN: Learning pixel-centric pairwise relations for figure/ground embedding, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVRP), 2016. https://doi.org/10.1109/CVPR.2016.26. http://ieeexplore.ieee.org/document/7780395. Accessed January 14, 2021.
Maire, M., Narihira, T., et al., Object contour detection with a fully convolutional encoder-decoder network, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVRP), 2016. https://doi.org/10.1109/CVPR.2016.28. http://ieeexplore.ieee.org/document/7780397. Accessed January 14, 2021.
Liu, Yu., Lew, M., et al., Learning relaxed deep supervision for better edge detection, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVRP), 2016. https://doi.org/10.1109/CVPR.2016.32. http://ieeexplore.ieee.org/document/7780401. Accessed January 14, 2021.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors declare that they have no conflicts of interest.
Additional information
Translated by A. Klimontovich
Rights and permissions
About this article
Cite this article
Kulikova, O.V., Dombayan, G.S. An Image Hashing Algorithm Based on a Convolutional Neural Network. Program Comput Soft 48, 407–411 (2022). https://doi.org/10.1134/S0361768822060068
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S0361768822060068