Perception of weld defects in digital X radiography images

<p><strong>X-radiography inspection techniques are generally used in non-destructive evaluation</strong></p><p><strong>industry. Manual assessment of the inspection may fail and turn into false assessment due</strong></p><p><strong>to a large number of examining while inspection process. Accordingly, incorrect</strong></p><p><strong>assessment through human vision may cause immense industry disaster. Therefore, it is</strong></p><p><strong>essential to examine through machine vision, which is capable to avoid false assessment.</strong></p><p><strong>Digital X-radiography has widely been used in Non-Destructive Testing (NDT) and</strong></p><p><strong>particularly in weld defect detection. Weld defects occurrence is an unavoidable problem</strong></p><p><strong>during the welding process. Most common weld defects some of which are porosity, gas</strong></p><p><strong>pore, tungsten inclusion, longitudinal crack, lack of penetration, and slag inclusion.</strong></p><p><strong>Digital image processing techniques are a foremost way to experiment in the NDT. The</strong></p><p><strong>detection and classification of weld defects depend on the quality of the digitized image,</strong></p><p><strong>which is subjected to certain factors, such as noise, the mode of the image histogram,</strong></p><p><strong>defects of different dimensions, indiscernible defects in the image background, and low</strong></p><p><strong>contrast or unevenly illuminated image. More accuracy can be achieved during classification</strong></p><p><strong>of weld defects are always be subject to the deliverables of low and mid-level image</strong></p><p><strong>processing techniques. Therefore, it is desirable to provide more importance for these levels</strong></p><p><strong>in the weld X-radiography image.</strong></p>