Information technologies and computer sciences

Image Recognition Using Bayesian Networks

Authors

A. V. Morozov
Zhytomyr Polytechnic State University ROR
V. L. Levkivskyi
Zhytomyr Polytechnic State University ROR
V. I. Piontkivsky
Zhytomyr Polytechnic State University ROR
DOI https://doi.org/10.31649/1997-9266-2024-175-4-115-121

Keywords

recognition Bayesian network learning testing MNIST probability neural network dataset

Abstract

Neural networks and Bayesian networks are powerful machine learning methods used to address a wide range of tasks. Neural networks are biologically inspired systems consisting of interconnected neurons that process information and transmit the results to other neurons. Bayesian networks, also known as belief networks or causal probabilistic networks, are a type of probabilistic graphical model. They are used to represent dependencies between variables and calculate the probabilities of different events. Bayesian networks enable to compute the probability of a certain event, taking into account other known events. They utilize Bayes’ theorem to update the probabilities of variables in the network. Their intuitiveness, flexibility, efficiency, and integrative nature make Bayesian networks relevant in many application areas. The aim of this work is to develop and test a Bayesian neural network for recognizing handwritten digits. In this study, a multilayer perceptron Bayesian network was developed and tested for the classification of handwritten digits. The MNIST dataset was used for model training, which contains 70,000 images of handwritten digits with labels. This dataset is widely used for testing image recognition algorithms. To evaluate the network’s effectiveness, a test subset of data containing 10,000 images of handwritten digits was used. The developed model demonstrated the accuracy of 93.92 %, which is a better result than other machine learning methods for recognizing handwritten digits. The given model could be useful for developing automatic text recognition systems, such as postal sorting machines and check scanners. The research demonstrates that the Bayesian network is a promising method for classifying handwritten digits, as confirmed by the study. Therefore, it can be concluded that Bayesian networks are not flawless. Their accuracy depends on the quality of data and the correctness of the model. However, if used correctly, they can be a powerful tool for detecting patterns and making decisions.

413 342

How to Cite

[1]
“Image Recognition Using Bayesian Networks”, Вісник ВПІ, no. 4, pp. 115–121, Aug. 2024, doi: 10.31649/1997-9266-2024-175-4-115-121.

Author Biographies

A. V. Morozov, Zhytomyr Polytechnic State University

Cand. Sc. (Eng.), Associate Professor, Vice Rector in Scientific and Pedagogical Work

V. L. Levkivskyi, Zhytomyr Polytechnic State University

PhD in Software Engineering, Associate Professor with the Chair of Computer Sciences

V. I. Piontkivsky, Zhytomyr Polytechnic State University

Assistant of the Chair of Software Engineering

References

Д. С. Клєщ, і В. М. Федорченко, «Аналіз підходів до розв’язання задач розпізнавання образів з використанням штучного інтелекту,» Системи управління, навігації та зв’язку. Збірник наукових праць, т. 1, вип. 71, с. 96-100, Бер 2023. https://doi.org/10.26906/SUNZ.2023.1.096 .
A. M. Ковальчук, Г. В. Марчук, і Д. К. Марчук , «Застосування згорткової нейронної мережі для розпізнавання рукописних символів,» Вчені записки ТНУ імені В. І. Вернадського, технічні науки, т. 30 (69), № 4, с. 68-73, 2019. https://doi.org/10.32838/2663-5941/2019.4-1/13 .
V. Levkivskyi, et al., “Available parking places recognition system,” CEUR Workshop Proceedings 4th Workshop for Young Scientists in Computer Science & Software Engineering: Virtual Event, vol. 3077, pp. 123-134, 2022. [Electronic resource]. Available: https://ceur-ws.org/Vol-3077/paper07.pdf .
В. Л. Левківський, Г. В. Марчук, В. В. Ципоренко, і Д. К. Марчук, Комп’ютерна програма «Алгоритмічно-програмне забезпечення обробки та аналізу потоку кадрів відеоданих, що надходять з камер міста». 2021 [Електронний ресурс]. Режим доступу: http://eztuir.ztu.edu.ua/bitstream/handle/123456789/8019/109822.pdf?sequence=1&isAllowed=y Дата звернення 10.03.2024.
A. Ali, et al., “Human Activity and Motion Pattern Recognition within Indoor Environment Using Convolutional Neural Networks Clustering and Naive Bayes Classification Algorithms,” Sensors 22, no. 3, 1016, 2022. https://doi.org/10.3390/s22031016 .
A. Lesniak, and F. Janowiec, “Risk assessment of additional works in railway construction investments using the Bayes network,” Sustainability, no. 19, pp. 5388, 2019. https://doi.org/10.3390/su11195388 .
L. Surace, et al., “Emotion recognition in the wild using deep neural networks and Bayesian classifiers,” in Proceedings of the 19th ACM International Conference on Multimodal Interaction (ICMI ‘17). Association for Computing Machinery, New York, NY, USA, pp. 593-597, 2017. https://doi.org/10.1145/3136755.3143015 .
MC. Roh, and SW. Lee, “Human gesture recognition using a simplified dynamic Bayesian network,” Multimedia Systems 21, pp. 557-568, 2015. https://doi.org/10.1007/s00530-014-0414-9 .
W. Chen, et al., “Wildfire risk assessment of transmission-line corridors based on naïve bayes network and remote sensing data,” Sensors, 21, no. 2, p. 634, 2021. https://doi.org/10.3390/s21020634 .
Z. Liu, et al., “Reliability evaluation of dynamic face recognition systems based on improved Fuzzy Dynamic Bayesian Network,” International Journal of Distributed Sensor Networks, no. 16(3), 2020. https://doi.org/10.1177/1550147720911558 .
V. Levkivskyi, N. Lobanchykova, and D. Marchuk, “Research of algorithms of Data Mining,” E3S Web of Conferences, vol. 166:05007, 2020. https://doi.org/10.1051/e3sconf/202016605007 ,
K. Shahab, “Novel swarm intelligence algorithms for structure learning of Bayesian Networks and a Comparative evaluation,” PHD thesis. Computer Engineering, Yasar University, Bornova / Izmir. 2020. https://doi.org/10.13140/RG.2.2.14284.85121 .
MNIST. 2015. [Online]. Available: https://paperswithcode.com/dataset/mnist Accessed on: 01.04.2024.