Automatic colour printing inspection by image processing

The inspection of colour printing products constitutes a very important quality control (QC) task in the printing industry. Many defects on such products may be inspected by current commercially available vision systems. However, for the inspection of complex colour prints, the capabilities and performance of available systems are limited. The current practice in the printing industry is to inspect complex colour products manually. This process is labour-intensive and the results are not reliable as they vary with the time, mood and personal skills of the inspectors. In this paper, the authors propose an algorithm to automate the colour prints inspection process, which incorporates colour histogram-based techniques for colour image processing and a neural network for image classification. Preliminary results have shown that this algorithm is able to inspect the defects of complex colour prints under varying illumination conditions.