Welding Defect Detection by Segmentation of Radiographic Images

Genetic algorithms to automatic weld bead detection in double wall double image digital radiographs

“…heuristic = 1.0 − weight |standard − candidate| MD (14) where MD denotes the maximum dissimilarity between two pixel values. Table II lists the "standard" values defined for each chromosome parameter, as well as the corresponding weights (defined through a refinement process) and normalizing factors, both used in (14).…”

“…Basically, this step consists in isolating the weld bead as a region of interest (ROI), where defects can be identified and segmented using different image processing techniques, including morphological bottom-hat filtering [3], Otsu's global thresholding, Sauvola's local thresholding [13], [14], [16], Gaussian filtering [16] and background subtraction [17]. Most of approaches for flaw identification assume that the weld bead has been manually isolated [4], [5], a drawback for most real world applications.…”

Optical Fiber Splicing Defect Segmentation Using Hybrid Active Contour

“…In the field of radiographic weld defects image segmentation, traditional techniques have been proposed such as thresholding and morphological approaches [3][4][5]. Recently, optimization techniques are introduced which tries to segment images by optimizing some criterion [6][7][8]. Active Contours [9][10][11][12][13][14][15][16][17][18] are the most popular techniques in this category where the idea is to drive an initial curve inside the image domain to be segmented to reach the boundaries of the objects of interest by minimizing energy where the curve is the argument of this energy [19].…”

An Non Destructive Test for the Detection of Weld Defects Using Image Processing

“…A method of segmenting the second category of defects in the welding joints is discussed in [9]. It makes use of the digitized radiographic image in case of low or noisy contrast images.…”