Inspection Algorithm of Welding Bead Based on Image Projection

The shear reinforcement of dual-anchorage (SRD) is used to enhance the safety reinforced concrete structures in construction sites. In SRD, welding create reinforcement, and after production, a quality inspection bead required. Since SRD inspected for by measuring both horizontal vertical lengths, it necessary obtain this information inspection. However, difficult inspect beads using existing methods based on segmentation, due similarity texture between base material, as well discoloration around welded area welding. paper, we propose an algorithm that detects image projection pixels classifies bead. This position brightness values image. proposed reduces amount computation time first specifying region interest then performing analysis. Results from experiments reveal accurately into good or bad classes obtaining all directions Furthermore, comparison tests with conventional algorithms demonstrate classification accuracy highest. will be helpful real-time field where fast accurate crucial.