NDE weld defect detection and feature extraction using segmentation approach

Abstract

In this paper, comparative study of morphological edge detection and region growing segmentation technique is introduced to detect and assess the flaws from the radiographic images. In the proposed method, segmentation algorithms are applied to detect the different types of flaws and calculate the necessary features such as major axis length, minor axis length, area, and perimeter. Computing time is optimised and algorithm is simpler to implement. These methodologies are compared and concluded to be effective for all possible nine types of weld flaws detection (slag inclusion, worm hole, porosity incomplete penetration, under cuts, cracks, lack of fusion, and weaving fault slag line). The experimental results show that our proposed method gives good performance for non-destructive evaluation (NDE) of radiographic images. © 2011 Inderscience Enterprises Ltd.