Neuro-Fuzzy Image Segmentation with Learning Function
https://doi.org/10.26907/1562-5419-2025-28-3-601-621
Abstract
This paper presents a neuro-fuzzy algorithm for high-speed grayscale image segmentation based on a modified defuzzification method using triangular membership functions. The aim of the study is to analyze the effect of simplifying the defuzzification formula on the accuracy and contrast of object selection. The proposed approach includes adaptive learning of the weight coefficient, which allows dynamically adjusting the defuzzification process depending on the target values. The paper compares the basic method of averaging membership values and a modified version taking into account nonlinear weights. Experiments conducted on 1024x720 images demonstrate that the developed algorithm provides high segmentation accuracy and improved object contrast with minimal computational costs. The results confirm the superiority of the proposed method over traditional approaches, emphasizing the prospects for applying artificial intelligence in computer vision problems.
About the Authors
Maksim Vladimirovich BobyrRussian Federation
Bogdan Andreevich Bondarenko
Russian Federation
References
1. Bobyr M.V., Milostnaya N.A., Bulatnikov V.A. The fuzzy filter based on the method of areas’ ratio // Applied Soft Computing, Volume 117, 2022, 108449, ISSN 1568-4946. https://doi.org/10.1016/j.asoc.2022.108449
2. Bobyr' M.V., Arkhipov A.Ye., Milostnaya N.A. Metod rascheta karty glubin na osnove myagkikh operatorov // Sistemy i sredstva informatiki. 2019. T. 29. № 2. S. 71–84. https://doi.org/10.14357/08696527190207
3. Lee D.H., Chen P.Y., Yang F.J. et al. “High-Efficient Low-Cost VLSI Implementation for Canny Edge Detection” // Journal of Information Science & Engineering, 2020. Vol. 36, No. 3. P. 34–57.
4. Koohi H., Kiani K. User Based Collaborative Filtering Using Fuzzy C-Means // Measurement. 2016. V. 91. P. 134–139. https://doi.org/10.1016/j.measurement. 2016.05.058
5. Yang Q., Sun L. A Fuzzy Complementary Kalman Filter Based on Visual and IMU Data for UAV Landing // Intern. Journal for Light and Electron Optics. 2018. V. 173. P. 279–291. https://doi.org/10.1016/j.ijleo.2018.08.011.
6. S. Eti, S. Yüksel, H. Dinçer. A machine learning and fuzzy logic model for optimizing digital transformation in renewable energy: Insights into industrial information integration // Journal of Industrial Information Integration. 2024. Vol. 42. P. 100734. https://doi.org/10.1016/j.jii.2024.100734. EDN MFEAPI.
7. Romanov A.A., Filippov A.A., Yarushkina N.G. Adaptive Fuzzy Predictive Approach in Control // Mathematics. 2023. Vol. 11, No. 4. P. 875. https://doi.org/10.3390/math11040875. EDN LRGVQT.
8. Bobyr M., Bondarenko B., Malyshev A. High-speed Fuzzy Inference Machine Learning Device Based on Single-Layer Area Ratio Defuzzifier // Intelligence Enabled Research: Proceedings of the 2024 Sixth Doctoral Symposium on Intelligence Enabled Research (DoSIER 2024), Dhupguri, Jalpaiguri, West Bengal, India, November 28–29, 2024. Jalpaiguri, West Bengal, India, 2025. P. 15–25. EDN FXFCKM.
9. Zimichev E.A., Kazanskiy N.L., Serafimov P.G. Prostranstvennaya klassifikatsiya putem integratsii izobrazheniy s ispol'zovaniyem metoda klasterizatsii k-means ++ // Komp'yuternaya optika. 2014. T. 38, No. 2. S. 281–286. https://doi.org/10.18287/01342452-2014-38-2-281-286
10. Pereyra M., McLaughlin S. Fast Unsupervised Bayesian Image Segmentation with Adaptive Spatial Regularisation // IEEE Transactions on Image Processing, 2017. Vol. 26, No. 6. P. 2577–2587. https://doi.org/10.1109/TIP.2017.2675165
Review
For citations:
Bobyr M.V., Bondarenko B.A. Neuro-Fuzzy Image Segmentation with Learning Function. Russian Digital Libraries Journal. 2025;28(3):601-621. (In Russ.) https://doi.org/10.26907/1562-5419-2025-28-3-601-621