Comparative Analysis of Gaussian Filter, Median Filter and Denoise Autoenocoder

Images can be enhanced and denoised with the help of filters. In this paper, we use a Gaussian filter, a Median Filter and a Denoising Auto encoder for noise removal. Gaussian filter is a linear type of filter which is based on Gaussian function. But the median filter is a non-linear type of filter. It preserves edge while removing noise. Deep Convolutional neural network (CNN) is able to handle Gaussian denoising at a certain noise level. We compare these three types of noise removers with the help of four types of evaluation techniques. We use time performance, Peak signal-to-noise ratio (PSNR), Structure Similarity (SSIM) and Normalization mean square error (NMSE) evaluation techniques for finding the best filter for removing noise from the image on different situations. We found that sometimes a Gaussian filter is better and sometimes the median filter is better depending on the iteration of the filter. Sometimes a denoise autoencoder is also better but it takes more time with respect to a Gaussian filter and a median filter. When we consider only the time parameter, then the Median filter gives better results in less time in comparison to a Gaussian filter and a denoise autoencoder filter.

I. Introduction

Computer analysis and segmentation are important tasks that can be performed on an image. During image acquisition and formation, the quality of images was reduced due to noise. This noise comes from many sources such as lighting conditions, displacements, etc. Two common types of noise are Gaussian noise and Salt & Pepper noise.