IoT-enabled computer vision-based parts inspection system for SME 4.0

Abstract

This paper presents a Computer vision-based Measurement (CViM) system for three-dimensional (3D) mechanical parts. The system integrates with internet of things (IoT) and demonstrates a low cost and modular implementation of SME 4.0 framework. A complete system design including hardware and software is presented. Three cameras are used to capture various images that expose different dimensions of the mechanical part. Back lighting is used to illuminate the part placed on the V-shaped translucent surface, which results in images with improved contrast thereby improving the measurement accuracy compared to front lighting. The software algorithm performs camera calibration to eliminate the lens distortion and pre-processing for image enhancement and noise elimination. Next, image binarization is performed to highlight the edges of the object. The desired dimensions are extracted from the image followed by pixel to physical measurement mapping. The system is tested by measuring physical dimensions of a drill bit and a screwdriver bit and it achieves an accuracy of tenth of a millimeter (mm). Several dimensions of the test parts are measured, such as, total length, back radius, groove length etc., which are the most number of dimensions considered, compared to previous studies. The results demonstrate that the maximum difference between the measured and the actual dimensions is ± 0.05 mm. A conceptual model of IoT-enabled CViM system for parts inspection in small and medium-sized industries is also presented. The system has a fairly low cost and is very suitable for such industries with similar accuracy requirements for their parts inspection.