Real-time forming error inspection system using computer vision for small-sized tubes

Recently, there has been an increasing demand for computer-vision-based measurement and inspection at the production line. So far lots of inspection processes are carried out by human workers, hence it is almost impossible to check the fault of all parts, coming from part-feeding system, with only human inspection because of time limitation as well as working hardship. Therefore, most of manual inspection is applied to specific samples, not all coming parts, and manual inspection neither guarantee consistent measuring accuracy nor decrease working time. Thus, in order to improve the measuring speed and accuracy of the inspection, a computer-aided measuring and analysis method is highly needed. In this paper, firstly a computer-vision-based small-sized tube inspection algorithm is proposed, where the tube images of front-view and side-view are acquired by CCD cameras. To reduce the vision processing time efficiently, a modified Hough transform is applied for calculate the geometry of straight line segments. A line-scanning method is adopted to calculate the center points of the inner and outer diameters. Secondly, the proposed algorithms are verified by the developed inspection machine. Finally, it is concluded that the proposed algorithm can be applied successfully to the inspection machine to guarantee the inspection requirements demanded from the company.