Welding defect detection in a radiographic image is an important topic in the field of industrial non‐destructive testing. To improve the accuracy of welding defect segmentation, a local image enhancement approach is proposed. In this algorithm, the requirement of contrast enhancement is considered when extracting the weld seam and segmenting the weld defect. The whole defect detection is conducted by three procedures: image enhancement, welding seam extraction, and defect segmentation. Firstly, a method for determining the Localised Pixel Inhomogeneity Factor (LPIF) is proposed. Then, based on the results of LPIF, the Otsu method is applied to segment the welding seam and defects are, identified by region growing algorithm. The authors compared LPIF with histogram equalisation, adaptive histogram equalisation, and contrast‐limited adaptive histogram equalisation algorithms and assessed its performance by using indicators such as image contrast, image definition, and edge intensity. Moreover, the authors compared the segmentation results of the enhanced defect images with the original image to further study the method's effect on weld defect segmentation. More than 70 images containing various types of defects are tested. The experimental results demonstrate that the quality of enhanced defect images is improved significantly, and has a high relative segmentation accuracy of more than 92%.
Offset surfaces have widespread applications in, for example, tool-path generation, robot path planning, error analysis, model design, layered manufacturing, and reverse engineering. This paper proposes a novel solution technique for the problem of surface offset on point clouds using direct point offsets along the normal vectors. In order to eliminate self-intersection and noise, a local geometric fitting surface created from neighbouring points is applied to check the validity of a point in the solution processing. Based on the generated offset surface, the tool paths can be generated using the direct projection method. Unlike traditional methods, the generated tool paths are represented by a series of cutter location (CL) points, and the placement and orientation of the actual cutting tool can be easily adjusted on the offset surface for avoidance of interference or overcut. Numerical experiments on several sets of scattered data points are presented, and the robustness and efficiency of the proposed approach is demonstrated by the results.
8 July 2008 in The International Journal of Advanced Manufacturing Technology