Defect Inspection System for Shape-Based Matching Using Two Cameras

This research is regarding the application of a vision algorithm to investigates various approaches for automated inspection in of gluing process using shape-based matching application in order to control the decision making concerning jobs and work pieces recognition that are to be made during system operation in real time. A new supervised defect detection approach to detect a class of defects in gluing application is proposed. Creating of region of interest in important region of object is discussed. Gaussian smoothing features in determining better image processing is proposed. Template matching in differentiates between reference and tested image are proposed. This scheme provides high computational savings and results in high defect detection recognition rate. The defects are broadly classified into three classes: 1) gap defect; 2) bumper defect; 3) bubble defect. 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