Automatic segmentation of ceramic materials with relaxed possibilistic C-Means clustering for defect detection

Abstract

<span>Auromatic inspection system is necessary for reliable quality control if ceramic materials to avoid operator subjectivity and fatigue in visual inspection. Automatic segmentation from material’s image is then the most important process to develop such an inspection system. In this paper, we propose a Possibilistic C-Means pixel clustering algorithm with fuzzy stretching to form the defect object in segmentation. In experiment using 50 images containing a certain amount of defects, the proposed method was successful in 49 cases or 98% of opportunities. That performance is roughly twice better than that of standard K-means clustering in defect object formation</span><span>Auromatic inspection system is necessary for reliable quality control if ceramic materials to avoid operator subjectivity and fatigue in visual inspection. Automatic segmentation from material’s image is then the most important process to develop such an inspection system. In this paper, we propose a Possibilistic C-Means pixel clustering algorithm with fuzzy stretching to form the defect object in segmentation. In experiment using 50 images containing a certain amount of defects, the proposed method was successful in 49 cases or 98% of opportunities. That performance is roughly twice better than that of standard K-means clustering in defect object formation.</span>

Automatic control of the sand granulation process to improve homogeneity in the manufacture of ceramic tiles

“…Likewise, in ceramic product manufacturing companies, there are different factors related to the quality of the production process and raw materials such as humidity, the dosage of clays and pigments, affect the appearance of the final product [31]. It turns out, then, that it is necessary to develop new technologies that allow improving and ensuring the quality of ceramic tiles, in order to guarantee the homogeneity of the components to obtain the final product and avoid waste of inputs [32], even more being known that many companies dedicated to the production of ceramic pieces generate a large amount of waste daily due to production defects [33]. In addition, the thing is that there are many companies worldwide, but in underdeveloped countries in the ceramic tile sector, that do not make use of automatic control technology and industrial automation [34].…”