An Optimal Fuzzy Filter for Gaussian Noise in Color Images Using Bacterial Foraging Algorithm

An Optimal Fuzzy Filter for Gaussian Noise in Color Images Using Bacterial Foraging Algorithm

Om Prakash Verma, Anil Singh Parihar, Shobha Tyagi

Department of Information Technology Delhi Technological University New Delhi, India opverma.dce@gmail.com, parihar.anil@gmail.com, tyagishobha@gmail.com

Abstract— This paper presents an optimal fuzzy filter for Gaussian noise in color images using Bacterial Foraging Algorithm (BFA) and cosine similarity. The filter makes use of the relationship between different color components of a pixel to remove the noise from the color images. Three color components of the RGB color space are paired as red-green, red-blue and green-blue. The adaptive cosine similarity between the central pixel and the neighboring pixels is estimated using these color pairs for noise removal. The membership function Large is defined and used to fuzzify similarity of each color component. Mean Square Error is used as an objective function, which is optimized using the bacterial foraging algorithm to learn the parameters of membership function Large. The correction term for the Gaussian filter is calculated using weighted average of the weights of all the neighboring pixels. The proposed Gaussian filter is found to be effective in eliminating noise from color images with the significant improvement in image quality. The experimental result on several color images proves the efficacy of the proposed fuzzy filter. Keywords— Fuzzy, Gaussian noise, Cosine similarity, Colorpair and BFA.

multichannel signal applications, the filters use fuzzy transformations of the angles among the different vectors to adapt to local data in the image. Fuzzy filters are easy to realize by means of simple fuzzy rules that characterize a particular noise. Major problem in removing Gaussian noise is to differentiate between noise and edges. In [4], the effective fuzzy derivatives are used for differentiating the noise and edge pixels in images corrupted with Gaussian...