الگوريتمي جديد براي آشكارسازي عيوب رنگي كاشي ها و سراميك ها بر پايه مدل سازي خوشه اي و الگوريتم هاي ژنتيكي

A New Algorithm for Color-Defects Detection of Ceramic Tiles through Clustering-Based Modeling and Genetic Algorithms

In this paper, a new algorithm is.proposed through the clustering-based modeling and genetic algorithms for color-defects detection of ceramic tiles. The algo~ithm consists of two stages: feature extraction and inspection. In the. former phase. th.e parameters of the algorithms are regulated by using one (some) reference defect-free ceramic - tile imagers) in order to produce the contextual model ofcolors. Then during the inspection phase th colors of the examined ceramic tiles images are compared to the color model; and each difference indica;es : color .defect. :ne proposed algorithm int~grates a new color clustering algorithm based on min-max criterion and genetic algont.hms s~ch that the f~rm~r IS. used by the later as the evaluation function. The experimental results ?n a database m~ludmg ~20 ceramic t~les ʹmages categorized to six groups demonstrated acceptable performance m terms ofsolution quality, computational burden, and adjustable sensitivity.