A Comparative Study of Removal Noise from Remote Sensing Image

TL;DR

This study compares the effectiveness of five different filters in removing three types of noise from remote sensing images, using MSE and PSNR metrics to determine the best method.

Contribution

It provides a comparative analysis of noise removal techniques specifically for remote sensing images, highlighting the most effective filters for different noise types.

Findings

Adaptive Median Filter performs best for Salt and Pepper noise.

Gaussian Filter is most effective for Speckle noise.

Mean Square Error and PSNR are useful metrics for evaluation.

Abstract

This paper attempts to undertake the study of three types of noise such as Salt and Pepper (SPN), Random variation Impulse Noise (RVIN), Speckle (SPKN). Different noise densities have been removed between 10% to 60% by using five types of filters as Mean Filter (MF), Adaptive Wiener Filter (AWF), Gaussian Filter (GF), Standard Median Filter (SMF) and Adaptive Median Filter (AMF). The same is applied to the Saturn remote sensing image and they are compared with one another. The comparative study is conducted with the help of Mean Square Errors (MSE) and Peak-Signal to Noise Ratio (PSNR). So as to choose the base method for removal of noise from remote sensing image.