Computer Vision for Automated Quality Inspection of Colour Printing Products
Quality inspection of colour printing products constitutes a very important QC task in printing industry. The current practice in industry is to inspect complex colour products manually. This process is labour-intensive and the results are not reliable. The types and causes of defects on colour prints are discussed in this paper. We present a novel algorithm to automate the printing inspection process, which incorporates colour histogram-based techniques for colour image processing and a neural network for image classification. The experimental results show that this algorithm is able to detect both registration and purity defects under varying illumination conditions.
KeywordsColour Histogram Gabor Filter Colour Distribution Moment Invariant Printing Industry
Unable to display preview. Download preview PDF.
- Yu X. H., Sodergard C. and Juna Y. J., 1993, On-line Control of Color Printing Quality by Image Processing. Proc. EEEE Region 10 Conf. Comput. Comm. Contr. Power Eng. Pp.1039–1041.Google Scholar
- Wang Y. S., Griffiths B. J. and Wilkie B. A., 1996, A Novel System for Colored Object Recognition. Computer in Industry, No. 32, pp.69–77.Google Scholar
- Hu M. K., 1962, Visual Pattern Recognition by Moment Invariants. IRE Trans. on Information Theory. Vol. 178, pp.179–187.Google Scholar