Abstract
Abstract
The use of machine vision systems has been made user-friendly, cost-effective, and flawless by the rapid development in the fields of advanced electro-optical and camera systems, electronics systems, and software systems. One such application of machine vision systems in the field of manufacturing is the inspection of a semi-finished or finished component during an ongoing manufacturing process. In this study, the camera’s intrinsic and extrinsic parameters were maintained constant, while red, green, and blue light sources were employed to measure the component diameter using pixel analysis. A novel approach was used in an IoT-based machine vision system where, on the same image, the smartphone camera was calibrated and the image diameter of the component under study was measured, which was found to be quite accurate. Four different cases were used in the error analysis of image diameter, in which experimental results show that under blue light, the percentage pixel error span is the largest at 0.2624% followed by 0.1422% under green light and 0.0903% under red light. Further, the use of four different cases was followed by the ‘Weighted Sum Model’, which optimized the percentage errors in estimated actual diameter precisely and effectively, where outcome results showed that the approximate percentage errors were determined within 0.8% for blue light, 0.5% for a red light, and 0.1% for a green light. The proposed IoT-based machine vision system was found to be robust and effective for on-machine measurement.