A System for Automatic Detection of Defects in Welding Radiographic Images

R. Vilar, J. Zapata, and R. Ruiz (Spain)

Keywords

Radiographic images, Weld inspection, Defect detection, Image processing, Thresholding.

Abstract

Radiographic inspection is a well-established testing method to detect welding defects. However, interpreta tion of radiographic films is a difficult task. The reliabil ity of such interpretation and the expense of training suit able experts the efforts being made towards automation in this field. In this paper, we describe an automatic detec tion system to recognize welding defects in radiographic images. Image processing techniques, including noise re duction, contrast enhancement, thresholding and labelling, were implemented to help in the recognition of weld re gions and the detection of welding defects. The results un derline the efficiency of the techniques used in the work.

Important Links:



Go Back