A Hybrid BiLateral Filter for Image Enhancement

Abstract

To remove the various types of noises that are either added in the image during capturing process or introduced into the image during transmission process, different types of Image Enhancement or noise reduction processes are applied. A good noise reduction method can reduce the noise level as well as preserve details of the image. This paper deals with removing the noise modeled with either a Gaussian or salt & pepper noise simultaneously from the images. The hybrid bilateral filter proposed by me is combination of bilateral filter and alpha trimmed filter. The hybrid bilateral filter is proven to perform better than or at least equal to the traditional bilateral filter. A image containing various degrees of Gaussian, salt & pepper, and mixed noise were used to evaluate the performance of this new denoising method. It is observed that the hybrid bilateral filter performed better than existing bilateral filter in both visual image quality and restored signal quantity.