Image Recognition Using Bayesian Networks
DOI:
https://doi.org/10.31649/1997-9266-2024-175-4-115-121Keywords:
recognition, Bayesian network, learning, testing, MNIST, probability, neural network, datasetAbstract
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.
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.
Downloads
-
pdf (Українська)
Downloads: 31
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
