An hybrid denoising algorithm based on directional wavelet packets

The paper presents an image denoising algorithm by combining a method that is based on directional quasi-analytic wavelet packets (qWPs) with the popular BM3D algorithm. The qWP-based denoising algorithm (qWPdn) consists of decomposition of the degraded image, application of adaptive localized soft thresholding to the transform coefficients using the Bivariate Shrinkage methodology, and restoration of the image from the thresholded coefficients from several decomposition levels. The combined method consists of several iterations of qWPdn and BM3D algorithms, where at each iteration the output from one algorithm updates the input to the other. The proposed methodology couples the qWPdn capabilities to capture edges and fine texture patterns even in the severely corrupted images with utilizing the sparsity in real images and self-similarity of patches in the image that is inherent in the BM3D. Multiple experiments, which compared the proposed methodology performance with the performance of six state-of-the-art denoising algorithms, confirmed that the combined algorithm was quite competitive.

Automated summary

This paper presents an image denoising algorithm that combines a directional quasi-analytic wavelet packets (qWPs) method with the popular BM3D algorithm. The proposed methodology updates the input and output of the two algorithms through multiple iterations, combining the capabilities of capturing edges and fine texture patterns and utilizing the sparsity and self-similarity properties. Experimental results show that the combined algorithm is competitive with state-of-the-art denoising algorithms.