A new approach for restoration of eddy current images

Eddy current images of defects are blurred due to convolution of point spre ad function of eddy current probe with defects. Disturbing variables such a s lift-off, surface roughness, and material property variations influence t he eddy current images. In order to restore the length, width, depth, and o rientation of surface-breaking defects in the presence of disturbing variab les, a new and comprehensive approach has been developed. This approach use s artificial neural network and image processing methods. Studies on austen itic steel plates confirm that through this approach it is possible to rest ore the spatial information of surface-breaking defects of uniform or slowl y varying depth and also to form their accurate three-dimensional pictures. This approach is fast as well as amenable for automation.