Multilevel Thresholding for Multi-Spectral Image Using Convolutional Fuzzy Clustering Algorithm and Gradient Multilayer Kernelized Perceptron
Keywords:
Multispectral image, multilevel thresholding, segmentation, classification, deep learningAbstract
When dealing with the issue of low-dimensional images, a multispectral image is made up of many bands with high dimensions. Both in terms of accuracy and calculation time, the current multilevel thresholding approaches are ineffective. Although they require a lot of work, 2D histogram-based approaches are better in terms of accuracy. This study suggests a unique method for segmenting and classifying various images based on multilayer thresholding and deep learning algorithms. Here, a variousimage is used as the input, and it has undergone noise removal, smoothening, and image resizing processes. Processed image has been segmented utilizing convolutional operation based fuzzy clustering with multilevel thresholding (Con_Fuz_Clus_MT) of the input image. Then this image has been classified using gradient multilayer Kernelized perceptron integrated with Darwinian optimization (GMKP-DO). Experimental findings confirmed by statistical analysis show that the newly created approach can produce accurate predictions. We demonstrate that combining two approaches—threshold-based and DL enhances cloud identification performance without requiring manual correction of automatically generated ground facts. Proposed technique attained classification accuracy of 93%, precision of 88%, recall of 85%, F-measure of 89%, ROC of 75% for flight dataset; Classification accuracy of 94%, precision of 92%, recall of 90%, F-measure of 90%, ROC of 41% for bird image dataset; Classification accuracy of 96%, precision of 82%, recall of 65%, F-measure of 56%, ROC of 45% for car image dataset.
Downloads
References
Henila, M., &Chithra, P. (2020). Segmentation using fuzzy cluster‐based thresholding method for apple fruit sorting. IET Image Processing, 14(16), 4178-4187.
Raja, P. S. (2020). Brain tumor classification using a hybrid deep autoencoder with Bayesian fuzzy clustering-based segmentation approach. Biocybernetics and Biomedical Engineering, 40(1), 440-453.
Dixit, M., Chaurasia, K., & Mishra, V. K. (2021). Dilated-ResUnet: A novel deep learning architecture for building extraction from medium resolution multi-spectral satellite imagery. Expert Systems with Applications, 184, 115530.
Almahasneh, M., Paiement, A., Xie, X., &Aboudarham, J. (2022). MLMT-CNN for object detection and segmentation in multi-layer and multi-spectral images. Machine Vision and Applications, 33(1), 1-15.
Ravi, C., Yasmeen, Y., Masthan, K. ., Tulasi, R. ., Sriveni, D. ., & Shajahan, P. . (2023). A Novel Machine Learning Framework for Tracing Covid Contact Details by Using Time Series Locational data & Prediction Techniques. International Journal on Recent and Innovation Trends in Computing and Communication, 11(2s), 204–211. https://doi.org/10.17762/ijritcc.v11i2s.6046
Chouhan, A., Agrawal, A., & Sur, A. (2021, December). Unsupervised Change Detection in Very High Resolution Multi-Spectral Images. In 2021 IEEE International India Geoscience and Remote Sensing Symposium (InGARSS) (pp. 293-296). IEEE.
Jena, B., Naik, M. K., Panda, R., & Abraham, A. (2021). Maximum 3D Tsallis entropy based multilevel thresholding of brain MR image using attacking Manta Ray foraging optimization. Engineering Applications of Artificial Intelligence, 103, 104293.
Wang, X., & Chen, Y. (2022). Research on Video Compression Algorithm Based on Deep Learning. In International Conference on Computer Engineering and Networks (pp. 1371-1378). Springer, Singapore.
Mr. Kaustubh Patil. (2013). Optimization of Classified Satellite Images using DWT and Fuzzy Logic. International Journal of New Practices in Management and Engineering, 2(02), 08 - 12. Retrieved from http://ijnpme.org/index.php/IJNPME/article/view/15
Maheswari, K. U., & Rajesh, S. (2022). Fused LISS IV Image Classification using Deep Convolution Neural Networks. INTERNATIONAL JOURNAL OF COMPUTERS COMMUNICATIONS & CONTROL, 17(5).
Cao, M. T., Nguyen, N. M., Chang, K. T., Tran, X. L., & Hoang, N. D. (2021). Automatic recognition of concrete spall using image processing and metaheuristic optimized LogitBoost classification tree. Advances in Engineering Software, 159, 103031.
Pal, R., Mukhopadhyay, S., Chakraborty, D., &Suganthan, P. N. (2022). Very high-resolution satellite image segmentation using variable-length multi-objective genetic clustering for multi-class change detection. Journal of King Saud University-Computer and Information Sciences.
Goyal, L. M., Mittal, M., Kumar, M., Kaur, B., Sharma, M., Verma, A., &Kaur, I. (2021). An efficient method of multicolor detection using global optimum thresholding for image analysis. Multimedia Tools and Applications, 80(12), 18969-18991.
Li, X., Ye, H., &Qiu, S. (2022). Cloud Contaminated Multispectral Remote Sensing Image Enhancement Algorithm Based on MobileNet. Remote Sensing, 14(19), 4815.
Navarro, P. J., Miller, L., Díaz-Galián, M. V., Gila-Navarro, A., Aguila, D. J., &Egea-Cortines, M. (2022). A novel ground truth multispectral image dataset with weight, anthocyanins, and Brix index measures of grape berries tested for its utility in machine learning pipelines. GigaScience, 11.
Vinaykumar, V., &Babu, J. A. (2022, July). Satellite Image Classification based on Adaptive Skip Connection-Convolutional Neural Network. In 2022 IEEE International Conference on Data Science and Information System (ICDSIS) (pp. 1-4). IEEE.
Labh, J. R., &Dwivedi, R. K. (2021, December). Extensive Study on Color and Light Translation of 2D Images using Machine Learning Approaches. In 2021 10th International Conference on System Modeling& Advancement in Research Trends (SMART) (pp. 290-294). IEEE.
Sangeetha, T., &Mohanapriya, M. (2022). A Novel Exploration of Plant Disease and Pest Detection Using Machine Learning and Deep Learning Algorithms. Mathematical Statistician and Engineering Applications, 71(4), 1399-1418.
Bharti, R., Saini, D., & Malik, R. (2021). A novel approach for hyper spectral images using transfer learning. In IOP Conference Series: Materials Science and Engineering (Vol. 1022, No. 1, p. 012120). IOP Publishing.
Ms. Elena Rosemaro. (2014). An Experimental Analysis Of Dependency On Automation And Management Skills. International Journal of New Practices in Management and Engineering, 3(01), 01 - 06. Retrieved from http://ijnpme.org/index.php/IJNPME/article/view/25
Dutta, T., Dey, S., Bhattacharyya, S., &Mukhopadhyay, S. (2021). Quantum fractional order darwinian particle swarm optimization for hyperspectral multi-level image thresholding. Applied Soft Computing, 113, 107976.
Oktem, F. S., Kar, O. F., Bezek, C. D., &Kamalabadi, F. (2021). High-resolution multi-spectral imaging with diffractive lenses and learned reconstruction. IEEE Transactions on Computational Imaging, 7, 489-504.
Popat, M., & Patel, S. (2022). Research perspective and review towards brain tumour segmentation and classification using different image modalities. Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 1-19.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
