In the field of remote sensing, the classification and recognition of multi-spectral images play a key role in understanding and monitoring our environment. This paper introduces an innovative method that leverages multi-threshold binarization for feature extraction in the classification and recognition of multi-spectral images. The core idea of this approach is to represent the intricate characteristics of multi-spectral images through a series of binary attributes, each of which captures specific image properties. One of the key findings of this research is the corre¬lation between the size of the training dataset and the performance accuracy of the classifier trained on this dataset. This relationship shows on the importance of having an appropriately sized training dataset to achieve high classification precision. Moreover, the approach offers a significant advantage in terms of efficiency compared to traditional convolutional neural network-based training processes. The reduced training time and faster operation of the method open up exciting possibilities for real-time recognition and classification of multi-spectral images. To validate the effectiveness of the approach, we conducted experiments on various test training datasets of multi-spectral images, and the results of these evaluations are presented. The findings highlight the promising potential of this method for a wide range of applications, including environmental monitoring, urban planning, and agricultural management, where accurate and real-time classification is essential. It is proposed a novel approach to multi-spectral image classification, employing multi-threshold binarization for feature extraction. The method’s ability to represent image features as binary characteristics offers a fresh perspective in the field of remote sensing. The findings of this research not only contribute to advancing the state of the art in multi-spectral image analysis but also provide a practical and efficient solution for real-time recognition and classification, aligning with the growing demands of various applications.

1. Gong, C.; Xingxing, X.; Junwei; Han, L.; Gui-Song, X. Remote Sensing Image Scene Classification Meets Deep Learning: Challenges, Methods, Benchmarks, and Opportunities. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2020, 13, 3735-3756. https://doi.org/10.1109/JSTARS.2020.3005403

2. Mohammad, R. Real-time statistical image and video processing for remote sensing and surveillance applications. Journal of Real-Time Image Processing. 2021, 18, 1435-1439. https://doi.org/10.1007/s11554-021-01168-x

3. Huang, X.; Banerjee, T.; Chen, K. Machine Learning based Video Processing for Real-time Near-Miss Detection. International Conference VTITS. 2020, 169-179. https://doi.org/10.5220/0009345400002550

4. Mutlag, W.; Ali, S.; Mosad, Z.; Hussein, B. Feature Extraction Methods: A Review. Journal of Physics. 2020, 1-10. https://doi.org/10.1088/1742-6596/1591/1/012028

5. Basavaiah, J.; Patil, C. Robust feature extraction and classification based automated human action recognition system for multiple datasets. International Journal of Intelligent Engineering and Systems. 2020, 13(1), 13-24. https://doi.org/10.22266/ijies2020.0229.02

6. Xiao, Y.; Chen, J.; Wang, Y.; Cao, Z.; Zhou, J.; Bai, X. Action recognition for depth video using multi-view dynamic images. Information Sciences, 2019, 480, 287-304. https://doi.org/10.1016/j.ins.2018.12.050

7. Zhuang B.; Shen C.; Tan M.; Chen P.; Liu L.; Reid I. Structured Binary Neural Networks for Image Recognition. Computer Vision and Pattern Recognition. 2019. 3.

8. Ding, R.; Liu, H.; Zhou, X. IE-Net: Information-Enhanced Binary Neural Networks for Accurate Classification. Electronics. 2022, 11. https://doi.org/10.3390/electronics11060937

9. Madaeni, F.; Chokmani, K.; Lhissou, R.; Homayouni, S.; Gauthier, Y. Convolutional neural network and long short-term memory models for ice-jam predictions. The Cryosphere. 2022, 16, 1447-1468. https://doi.org/10.5194/tc-16-1447-2022

10. Rusyn, B.; Korniy, V.; Lutsyk, O.; Kosarevych, R. Deep Learning for Atmospheric Cloud Image Segmentation. International Scientific and Practical Conference on Electronics and Information Technologies. 2019, 188-191. https://doi.org/10.1109/ELIT.2019.8892285

11. Feng, X.; He, L.; Cheng, Q.; Long, X.; Yuan, Y. Hyperspectral and Multispectral Remote Sensing Image Fusion Based on Endmember Spatial Information. Remote Sensing. 2020, 12(6). https://doi.org/10.3390/rs12061009

12. Yuan, X.; Shi, J.; Gu, L.C. A review of deep learning methods for semantic segmentation of remote sensing imagery. Expert Systems with Applications. 2021, 169. https://doi.org/10.1016/j.eswa.2020.114417

13. Farshi, T.; Demirci, R. Multilevel image thresholding with multimodal optimization. Multimedia Tools and Applications. 2021, 80, 15273-15289. https://doi.org/10.1007/s11042-020-10432-4

14. Rusyn, B.; Lutsyk, O.; Kosarevych, R.; Maksymyuk, T.; Gazda, J. Features extraction from multi-spectral remote sensing images based on multi-threshold binarization. Scientific Reports. 2023, 13. https://doi.org/10.1038/s41598-023-46785-7