The automation of industrial quality control based on artificial (computer) vision can avoid some of the problems associated with tedious and repetitive manual procedures that will often originate operator errors. Automatic quality control can also be applied uninterruptedly. However, strategies of that sort have some drawbacks. One is associated with image acquisition under controlled illumination conditions. The material characteristics of an object for analysis will also influence the final result. For example, the illumination of metallic objects or objects with metallic finishes will generate specular reflection and shadow, which must be minimized. The illumination effect on subsequent processing stages may be analysed by applying segmentation techniques (based, for instance, on clustering strategies), to identify the number of objects. In this study, a MATLAB desktop application for image processing was developed, where illumination-invariant transforms were applied prior to image segmentation, to improve the quality of segmentation results. A set of illumination-invariant transforms and clustering-based segmentation methods were applied and the segmentation quality (if there was a groundtruth image) was quantified. The experimental results obtained with 4 illumination-invariant algorithms, 4 clustering-based segmentation algorithms, and 29 images of metal parts acquired by factory operators and manually segmented by researchers, demonstrated significant improvement to image segmentation following the application of illumination-invariant transforms.
