Abstract
Machine vision systems are of paramount importance in the context of contemporary industrial quality control, wherein the reliability of object detection is contingent upon the conditions of image acquisition. It is evident that illumination is a pivotal factor in the context of inspection performance, exerting a substantial influence on factors such as image contrast, feature visibility, and detection accuracy. The present study investigates the influence of multispectral illumination on the detection of coloured polymer samples using a Keyence intelligent vision system. The experimental investigation was conducted using geometrically identical samples manufactured from the same material but differing in surface colour. Four colour variants, namely white, black, violet, and orange, were evaluated under seven illumination conditions, including white, red, green, blue, infrared (IR), ultraviolet (UV), and ambient mode illumination. The acquired images were then subjected to analysis with respect to the visibility of geometric features, contour sharpness, and overall detection reliability. The findings of the present study demonstrated that the illumination wavelength exerts a significant influence on the detectability of objects and the quality of the resulting images. White illumination was found to provide the most consistent performance across all the samples that were tested. In addition, specific combinations of object colour and illumination spectrum were found to produce enhanced feature visibility. Infrared illumination exhibited favourable outcomes for surfaces of a darker hue, whilst ultraviolet illumination enhanced the visibility of specific features on samples of a coloured nature. The findings presented herein corroborate the significance of illumination selection in industrial machine vision applications and furnish pragmatic recommendations for the optimisation of inspection conditions when employing intelligent vision sensors. The findings may inform the development of more reliable automated quality control systems in Industry 4.0 and Industry 5.0 environments.