The Research On X-ray Digital Image Processing And Defects Detection Method

X-ray defect detection is one of the primary methods in non-destructive testing of industrial products and is also widely applied. At present, primary methods of detection defects in the weld is still film imaging and image intensifier real time imaging and done by human interpreter both foreign and domestic, The problems of this process are subjective, inconsistent, labor intensive and fatigue of interpreter. So computer-aided detection of weld defects has been concerned. However, as a result of the imaging condition, the object as well as the algorithm complexity and the limitations, in the practical application, there are still many issues to be studied further.This task takes the X-ray weld seam image as the research object, in view of the X-ray image characteristics of low contrast, high image noise and fluctuated background, fuzzy weld seam edge and more texture with linear diode arrays real-time imaging in the petroleum welded pipe.Matlab simulation software is used to analysis methods of smoothing noise, gray transform enhancement, and image segmentation for image processing.After methods of linear, non-linear of space and frequency filtering, threshold segmentation, edge detection and mathematical morphology of image segmentation are Compared, methods of the adaptive median filtering, the variance ratio of interclass and intraclass segmentation, and mathematical morphology was used to decrease noise of the original welded seam image, to intersect welded seam region. According to the location and shape the information of weld seam defects, the weld seam is caught on high frequency enhancement,a method of simple and effective detection is proposed.Simulation results indicated that the adaptive median filtering effectively removes noise, and maintain the details of welded seam and defection edge; the variance ratio of interclass and intraclass segmentation could accurately distinguished between the welded seam metal and the base metal together with mathematical morphology method; high frequency enhancement extrudes the welded seam center, consequently defects would be detected.