Weather Classification using Convolutional Neural Networks

Abstract

Deep learning is one of the most popular fields in recent years and is applicable to many fields, such as computer vision and image processing. In this paper, we describe a new weather image classification technique using Alexnet and Resnet convolutional neural networks (CNN) combined with a multi- class Support Vector Machine (SVM). Experimental results in weather database, desnownet, and d-hazy datasets demonstrate that the proposed method achieves good performance in weather classification.