Research Journal of Engineering and Technology

Image de-noising has become an important step in digital image processing and removing unwanted noisy from the image is important area of the research. The project assign to generate the noise free images from the noisy images has consider the three objective which are (1) suppression of the noise effectively in uniform regions, (2) preserve edges and other similar image characteristics and (3) provide a visually natural appearance. In this project the hybrid nature of technique is used which include fractional order for determination diffusion coefficients and a residual error term and wavelet transform method for decomposition of images into low and high frequency. The diffusion coefficients can be used effectively for noise removal and the residual error term can help to prevent image distortion. In this project simulated performance of the image de-noising are done using MATLAB and peak signal-to-noise ratio (PSNR), Normalized Cross Correlation (NCC), Normalized Absolute Error (NAE) and Structural Content (SC) are used to evaluate the method.