• Tanvi Rajnikantbhai Navik
• Dr. Mukta Agarwal

The image pixel values are grouped into meaningful groups using the Machine Learning approach. Machine learning has the capacity to classify remotely sensed images effectively and efficiently. Taxonomy of machine learning Methods may be divided into three groups: 1) supervised, 2) unsupervised, and 3) reinforcement. Machine Learning classification necessitates the selection of the best classification technique based on the demands. Machine Learning methods are the subject of the present research project. The outcomes of two approaches, SVM and ANN, on satellite image categorization methods are compared in this study. Artificial Neural Networks and Support Vector Machines are used to automatically identify and classify damaged structures. The results are then compared to those obtained using traditional change detection methods in a comparative study. It has been discovered that the wavelet-based change detection approach produces better identifying information for damaged structures than traditional methods. In this study, a newly introduced texture-wavelet analysis on roof-tops is used to determine the proportion of each damaged building's damaged area, and the findings are confirmed by personally counting the damage pixels. As the percentage area of damage grows, a positive increase in the retrieved statistical characteristics is noted, adding to the accuracy of the identification approach.

Machine Learning, Classification, Satellite Image Classification, Satellite Remote sensing, Support Vector Machine, Artificial Neural Network, Damage Building, Wavelet-based change detection method, Texture-wavelet analysis

"Machine Learning Algorithms with Satellite Image Classification for Damaged Building Based on Support Vector Machine (SVM) and Artificial Neural Network (ANN) classification and comparison", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.d741-d753, April-2022, Available :http://www.jetir.org/papers/JETIR2204388.pdf

"Machine Learning Algorithms with Satellite Image Classification for Damaged Building Based on Support Vector Machine (SVM) and Artificial Neural Network (ANN) classification and comparison", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppd741-d753, April-2022, Available at : http://www.jetir.org/papers/JETIR2204388.pdf