IMPROVING THE ACCURACY OF ANALYSIS AND PROCESSING OF COMPLEX STRUCTURED IMAGES
DOI:
https://doi.org/10.26906/SUNZ.2025.2.137Keywords:
complex structural image, point object, planar object, segmentationAbstract
Topicality. Complex-structured images (CSI) tend to consolidate graphs of various types and hetero-hierarchy of semantic plans, which leads to the need to use hybrid and iterative algorithms specific to this type of images. The object of the study is the process of analyzing and processing raster CSI. The subject of the study is models and increasing the accuracy and productivity of CSI analysis and processing algorithms. The purpose of the study is to increase the accuracy and productivity of CSI analysis and processing algorithms. Research results. In the course of the work, an analysis of the current state of analysis and processing of raster complex-structured images was conducted. Research was conducted on approaches to localization and determination of types of segmented objects. Research was conducted on approaches to pattern recognition and their grouping. An improved and researched method for increasing the accuracy of analysis and processing of CSI. Conclusion. The proposed approach allowed to increase the accuracy of analysis and processing of complex structural images due to segmentation, localization, recognition and grouping of point, linear and planar objects, which are based on the integrated use of known methods.Downloads
References
1. Zhang, Zh. MKANet: An Efficient Network with Sobel Boundary Loss for Land-Cover Classification of Satellite Remote Sensing Imagery. Remote Sens. 2022. No. 18:4514. doi: https://doi.org/10.3390/rs14184514
2. Li, H. Intelligent Map Reader: A Framework for Topographic Map Understanding With Deep Learning and Gazetteer. IEEE Access. 2018. V. 6. P. 25363-25376. doi: https://doi.org/10.1109/ACCESS.2018.2823501
3. Petrovska, I., Kuchuk, H. (2023). Adaptive resource allocation method for data processing and security in cloud environment. Advanced Information Systems, 7(3), 67–73. doi: https://doi.org/10.20998/2522-9052.2023.3.10
4. Zakharchenko, A., Stepanets, O. (2023). Digital twin value in intelligent building development. Advanced Information Systems, 7(2), 75–86. doi: https://doi.org/10.20998/2522-9052.2023.2.11
5. Li, G., Liu, Y., Wu, J., Lin, D., Zhao, Sh. (2019). Methods of Resource Scheduling Based on Optimized Fuzzy Clustering in Fog Computing. Sensors, MDPI, 19(9). doi: https://doi.org/10.3390/s19092122
6. Кучук Н. Г., Мерлак В. Ю., Скородєлов В. В. Метод зменшення часу доступу до слабкоструктурованих даних. Сучасні інформаційні системи. 2020. Т. 4, № 1. С. 97-102. doi: https://doi.org/10.20998/2522-9052.2020.1.14
7. Zuev, A., Karaman, D., Olshevskiy, A. (2023). Wireless sensor synchronization method for monitoring short-term events. Advanced Information Systems, 7(4), 33–40. doi: https://doi.org/10.20998/2522-9052.2023.4.04
8. Moreno-Garcia C. F., Elyan E., Jayne C. New trends on digitisation of complex engineering drawings. Neural Computing and Applications. 2019. V. 31(6). P. 1695-1712. doi: https://doi.org/10.1007/s00521-018-3583-1
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Andriy Kovalenko, Vazha Chkheidze, Olena Sevostianova, Oleksandr Fomichov
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
