Automatic Defect Extraction and Segmentation in Welding Seam Based on X-Ray Images

In light of the characteristic of thin-wall weld joint in X-ray image, Flaw-edge extraction algorithm and image enhancement algorithm which is based on mathematical morphology are proposed in the study of flaw extraction technique. Therefore, the area of flaw and background can be removed successfully. On this basis, there are two algorithms to identify different flaw types: one is that spatial domain transform to extract flaw edge for clack, the other one is mathematical morphology which is combined with iteration threshold to extract flaw edge for pore; Experimental results show that both of algorithms can implement flaw extraction and segmentation automatically, which is lay a good foundation for flaw feature parameter extraction and recognition.