Teachers Login Form



Pupils Login Form


Radiographic Weld Images Denoising Using Wavelet-Based Technique

Auteurs : Fatma Zohra BOUDANI, Nafaa Nacereddine
Année : 2016
Domaine : Electronique
Type : Communication
Conférence: 7th African Conference on Non Destructive Testing (ACNDT 2016)
Résumé en PDF : (résumé en pdf)
Fulltext en PDF :
Mots clés : radiographic images, weld defect, X-ray, noise, wavelet

Résumé :

Improving the quality of X-ray images is an important aspect for many applications, for instance, industrial nondestructive examinations and medical diagnosis. The industrial radiographic images are widely used for weld defects detection, and that is a crucial task to ensure safety in many sectors. These images have a low contrast and are often corrupted by noise which makes it difficult to locate the flaws automatically. Therefore, several image denoising methods have been applied on radiographic images to increase the effectiveness of their analysis and observation. In this paper, we apply a denoising method using diffusion-inspired shrinkage functions in the wavelet domain to reduce noise in radiographic weld images. This approach is compared to some existing denoising methods to evaluate the performance of the filtering algorithms. The experimental results show that this wavelet diffusion technique outperforms traditional wavelet-based denoising methods and offers an adequate and promising filtering.