Ranking and selecting the appropriate filter for Gaussian noise removal with TOPSIS method

Document Type : Research Paper


1 Ph.D Student of Mathematics, Tabriz Branch, Islamic Azad University, Tabriz, Iran.

2 Department of Mathematics, Tabriz Branch, Islamic Azad University Tabriz, Iran

3 Department of Computer engineering, Tabriz Branch, Islamic Azad University Tabriz, Iran


Image noise removal is very important in most image processing analysis. Among various noises that can damage the image, Gaussian noise is one of the most notable. There are several ways to reduce image noises, including transformation-based methods, filter-based methods, and non-local methods.In most of the methods, only one criterion (i.e. signal-to-noise ratio) is used to reduce the image noise, and even some methods do not retain image quality and structural details of the image such as lines and edges.In this paper, the TOPSIS method was used to rank different filters of Gaussian noise filtering based on various criteria that influence the evaluation of image quality.In fact, regarding the standard deviation degree of the Gaussian noise, it was intended to know what kind of noise removal filter which contains the considered criteria should be used. The computational results of the proposed method were evaluated on different images with various standard deviation of Gaussian noise, and consequently, the filter has been specified corresponding to the degree of Gaussian noise for the application.