Abstract
In the present work, a Hopfield neural network is built for recognizing handwritten digit images contained in the MNIST database. Ten Hopfield neural networks are built, one for each digit. The cluster centers, which are constructed using the Kohonen neural network, are taken as objects for “memorizing”. Two methods are proposed, which act as an auxiliary stage in the Hopfield neural network, and an analysis of the methods is carried out. The error is determined for each method, and the pros and cons of using them are identified.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Z. Kayumov, D. Tumakov, S. Mosin, Combined convolutional and perceptron neural networks for handwritten digits recognition, in Proceedings of 22th International Conference on Digital Signal Processing and its Applications, pp. 1–5 (2020)
Y. Xu, W. Zhang,On a clustering method for handwritten digit recognition. 3rd Int. Conf. on Intelligent Net. and Intelligent Syst. 112, 115 (2010)
S.V. Aksenov, Organization and use of neural networks (methods and technologies). Tomsk:NTL (2006)
C. Ramya, G. Kavitna, K. Shreedhara,Recalling of images using hopfield neural network model. national conference on computers, communication and controls -11 (N4C-11) (2011)
M. Rexy, K. Lavanya, Handwritten digit recognition of MNIST data using consensus clustering. Int. J. Recent Technol. Eng. 7(6), 1969–1973 (2019)
L.C. Munggaran, S. Widodo, A.M. Cipta, Handwritten pattern recognition using Kohonen neural network based on pixel chatacter. Int. J. Adv. Comput. Sci. App. 5(11), 1–6 (2014)
S. Nhery, R. Ksantini,M.B. Kaaniche, A. Bouhoula, A novel handwritten digits recognition method based on subclass low variances guided support vector machine. 13th Int. Joint Conf. on Comput. Vision, Imaging and Computer Graphics Theory and App. (4), 28–36 (2018)
S.A. Shal, V. Koltun, Robust continuous clustering. Proc. Natl. Acad. Sci. USA 114(37), 9814–9817 (2017)
E. Miri,S.M. Razavi, J. Sadri, Performance optimization of neural networks in handwritten digit recognition using intelligent fuzzy c- means clustering, in 1st International Conference on Computer and Knowledge Engineering, pp. 150–155 (2011)
S. Pourmohammad, R. Soosahabi, A.S. Maida, An efficient character recognition scheme based on k-means clustering, in 5th International Conference on Modeling, Simulation and Applied Optimazation, pp. 1–6 (2013)
B.Y. Li, An experiment of k-means initialization strategies on handwritten digits dataset. Intell. Inf. Manag. 10, 43–48 (2018)
A. Fahad, N. Alshatri, Z. Tari, A. Alamari, A. Zomaya, I. Khalil, F. Sebti, A. Bouras, A Survey of Clustering Algorithms for Big Data: Taxonomy & Empirical Analysis. IEEE transactions on emerging topics in computing, (2014)
A. Ullah, J. Ahmad, K. Muhammad, M. Sajjad, S.W. Baik, Action recognition in video sequences using deep bi-directional LSTM with CNN features. Special Section on Visual Surveillance and Biometrics: Practices, Challenges, and Possibilities 6, 1155–1166 (2018)
K.N. Mutter, I.I. Abdul Kaream, H.A. Moussa, Gray image recognition using hopfield neural network with multi-bitplane and multi- connect architecture, in International Conference on Computer Graphics, Imaging and Visualisation (CGIV'06) (2006). https://doi.org/10.1109/CGIV.2006.49
A. Basistov, G. Yanovskii, Comparison of image recognition efficiency of bayes, correlation, and modified hopfield network algo- rithms. Pattern Recognit. Image Anal. 26, 697–704 (2016)
I.S. Senkovskaya, P.V. Saraev, Automatic clustering in data analysis based on Kohonen self-organizing maps. Bulletin of MSTU. Nosova I., G.: No. 2, pp.78–79 (2011)
Z. Kayumov, D. Tumakov, S. Mosin, Hierarchical convolutional neural network for handwritten digits recognition. Procedia Comput. Sci. 171, 1927–1934 (2020)
J. Lampinen, E. Oja, Clustering properties of hierarchical self-organizing maps. J Math Imaging Vis 2, 261–272 (1992)
F. Murtagh, M. Hernández-Pajares, The Kohonen self-organizing map method. an assessment. J. Classif. 12, 165–190 (2012)
P.Y. Simard, D. Steinkraus, J. Platt, Best practices for convolutional neural networks applied to visual document analysis, in Seventh International Conference on Document Analysis and Recognition, vol. 1, pp. 958–963 (2003)
D. Ciresan, U. Meier, J. Schmidhuber, Multi-column Deep Neural Networks for Image Classification. in IEEE Conference on Computer Vision and Pattern Recognition, CVPR, pp. 3642–3649 (2012)
Acknowledgements
This paper has been supported by the Kazan Federal University Strategic Academic Leadership Program (“PRIORITY-2030”).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Latypova, D., Tumakov, D. (2022). Peculiarities of Image Recognition by the Hopfield Neural Network. In: García Márquez, F.P. (eds) International Conference on Intelligent Emerging Methods of Artificial Intelligence & Cloud Computing. IEMAICLOUD 2021. Smart Innovation, Systems and Technologies, vol 273. Springer, Cham. https://doi.org/10.1007/978-3-030-92905-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-92905-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-92904-6
Online ISBN: 978-3-030-92905-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)