DefinePK

Abstract

This paper proposed the application of vision algorithm using shape-based matching approach to investigate various approaches for automated inspection in gluing process. This approach to identify the defect occurs in gluing process in automation industry. The processes involve using new supervised defect detection approach to detect a class of defects such as gap, bumper and bubble defect. The combination of creating of region, Gaussian smoothing and template matching being implemented in shape-based matching to provide provides high computational savings and results in high defect detection recognition rate. A new low-cost solution for gluing inspection is also included in this paper. The defects occur provides with information of height (z-coordinate), length (y-coordinate) and width (x-coordinate). This information gathered from the proposed two camera vision system for conducting 3D transformation. Results regarding this method approximately 95.4% recognition rate better than other researchers in welding and fabric field approximately 94.3% and 92% respectively. This result is based on 15 tested images with approximately 100 defects occur and being tested for 10 times to get better recognition rate.