Image denoising based on adaptive spatial and Wavelet Thresholding methods

The denoising of digital images degraded by various types of noises is a major problem in digital image processing. This paper presents a new hybrid image denoising method fusing Bilateral Filter (BF), Wavelet Thresholding, Multiscale products Wavelet Thresholding for image denoising. With the help of nonlinear combination of information of adjacent pixel, bilateral filter smoothen the edges and preserve the edge details of the images. In the first stage, the noisy image is passed through Bilateral Filter (BF) but only some amount of noise get reduced but the image gives a blurred appearance and it is has a problem with extreme outliers. Hence to preserve the edge details and reduce the blur effect, wavelet thresholding and adaptive wavelet thresholding is applied with the help of multiscale product rule in the next stages. In the second stage, the bilateral filter output is passed through the wavelet thresholding method and some amount of blurring gets reduced. During the third stage, the Dyadic Wavelet Transform is applied and an adaptive threshold is calculated with the help of multiscale product adaptive thresholding rule and implemented on the multiscale products rather than on the wavelet coefficients. While applying the threshold rule, the important features like edges, curves and textures can be identified. The proposed method helps to preserve the edges while suppressing the noise. The experimental results prove that the proposed image denoising method is competitive when compared to other methods in reducing various types of noise. The proposed method outperforms other methods both visually and in case of objective quality peak-signal-to-noise ratio (PSNR).