Multi-Weather Classification using Deep Learning: A CNN-SVM Amalgamated Approach

Weather detection and multi-classification based on image processing are of great importance in various fields such as transportation, agriculture, and energy management. This study presents a novel approach for the detection and multi-classification of weather conditions using an amalgamated deep learning (DL) model of Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs). The proposed model is evaluated on a dataset of 10,000 self-collected images consisting of five different weather conditions: sunny, rainy, windy, snowy, and cloudy. Our approach demonstrates a high level of accuracy and robustness in identifying different weather conditions. The findings demonstrate that the suggested model is superior to other state-of-the-art weather detection models, achieving an overall accuracy of 97.24% for multi-classification. Furthermore, we conducted a comprehensive analysis to determine the significance of various parameters on the performance of the proposed model. Overall, our study contributes to the development of efficient and reliable weather detection systems that can aid decision-making in various applications.