Image Denoising

Digital images are often corrupted by noise. Therefore, a lot of methods were designed for the purpose of denoising images. This paper describes and compares three of these methods: low-pass filters, bilateral filter and wavelet thresholding. Low-pass filters are linear filters applied on image by convolution. Their disadvantage is making images smooth. Bilateral filter is an extension of low-pass filters. It smooths images as well, however it preserves edges. Wavelet thresholding is a more complex method using wavelet transform for time-frequency representation of image whose coefficients are thresholded. The downside of this method is making artifacts in images. The PSNR and SSIM methods are used for measuring image quality