Diffusion In The Wavelet Domain For Denoising Radiographic Images Of Welding Defects

Abstract

In this paper, we aimed to filter radiographic weld images to facilitate weld defects detection and to improve the automatic industrial inspection. The noisy images were contaminated by three types of noise: the multiplicative speckle noise, the additive Gaussian white noise, and the mixed noise combining the two kinds of noise. Wavelet-based filters and anisotropic diffusion techniques have proven their worth in reducing both Gaussian additive noise and speckle noise. We presented in this work a filtering algorithm based on diffusion in the wavelet packet domain to enhance the quality of the noisy weld images. Comparing the performance of this approach to other wavelet based methods, experiments proved the wavelet packet diffusion’s effectiveness in reducing noise and preserving defects details.