Denoising of A Mixed Noise Color Image Through Special Filter

Abstract

Image denoising is the manipulation of the image data to produce a visually high quality image. At present there are a variety of methods to remove noise from digital images. There are different types of filters like mean filter, median filter, bilateral filter, wiener filter etc. to remove a single type of noise such as salt and pepper noise, speckle noise, Gaussian noise etc. But if the image is corrupted by mixed noise then these filters do not remove the noise exactly. Here a white flower image has been taken for denoising purpose. The white flower image is corrupted by mixed noise at zero mean and different variances to produce different noisy images at zero mean and respective variances. Noisy image is denoised by discrete wavelet transform (DWT) denoising technique using ‘Haar’ wavelet and different filters like median filter, wiener filter and bilateral filter one-by-one to produce noise free image as much as possible. Different parameters like MSE (mean square error), PSNR (peak signal to noise ratio), RMSE (root mean square error), SNR (signal to noise ratio) and SSIM (structural similarity index) estimate the performance of all filters. Special filter is designed with the help of these performance estimations so that a better filter for mixed noise image denoising purpose can be implemented. All mixed noisy images are denoised by the special filters and their performance parameters are estimated. The special filter is a combination of various filters and denoising techniques to remove of mixed noise from a digital image. The comparisons between noisy and denoised images of the special filter and other filters are presented in the form of graphs and tables.