Performance Analysis of Different Preprocessing Techniques for Cyclone Prediction

Cyclone is a prevailing spinning storm which has strong winds and rain. It encompasses several related features like eyes, rainfall intensity, pathway, wind speed, storm surges, etc. Cyclone prediction is a major issue when the cloud intensity images exhibit feature patterns at several stages of growth. The recently developed artificial intelligence (AI) techniques can be utilized for effective classification of images for cyclone prediction. Several challenging issues exist in the cyclone prediction process such as high prediction error, poor image quality, noise, high complexity, etc. Image pre-processing techniques can be applied for improving the image quality and eliminating the noise that exists in it. In this aspect, this study focuses on comprehensive performance analysis of different image filtering techniques for cyclone prediction. To accomplish this, two types of noises such as salt & pepper and Gaussian noise are added to the input images. Besides, three filtering approaches namely Weiner filter (WF), Gabor filter (GF), and Gaussian filtering (GUF) are used. The filtering approaches help to eradicate the noise and thereby improve the image quality. A detailed simulation analysis is performed on various cyclone images and the results are assessed interms of different measures. The comparative results ensured that the WF technique has the ability to achieve better performance over the other GF and GUF techniques.