Colour and proportion of grains measurement in through-body porcelain tiles by means of image processing

A common demand in the production of through-body porcelain tiles is the visual uniformity of the produced tiles. We assume that their visual appearance can be controlled by properly acting over the process control. This paper presents an image processing method for obtaining a feedback for it. The method estimates two important properties, which are colour and proportion of each kind of grains forming the tile. It consists of two steps: a colour segmentation by applying the clustering algorithm 'Fuzzy C-Means', and the centres refinement of the former segmentation, proposed by us. The centres refinement proposal is based on the colour information and the colour mixing process. The experimental results show that the measurements of the colour and the proportion of grains obtained with the centres refinement, are more accurate compared to the ones obtained with 'Fuzzy C-Means'.