A method for defect segmentation in digital radiographs of pipeline girth welds

Radiography, one of the chief methods for inspecting welds, is rapidly becoming an all-digital technology. Once the radiographic image is captured in a digital format, the next logical step is to use digital technology to automate interpretation of the radiographic image. A key step in the automated interpretation process is the segmentation of indications from the background. This paper describes the use of a multiscale method for image segmentation and demonstrates its use on laboratory test pieces of pipeline girth welds.