Improved Canny Edge Detector in Ceramic Tiles Defect Detection

Image processing is very often present as a method for visual inspection in industry. Automated systems for visual inspection are very important part of the quality control in production line. Quality control has been mostly performed in hard work conditions. Using automated visual systems quality control becomes easier. It performs faults detection and final quality control. In this paper we present the method for faults detection based on edge detection techniques. Edges and faults on ceramic tiles were detected using Canny edge detector. Problem of defining hysteresis thresholds was resolved with a histogram subtraction method. Method was implemented on various types of faults: edge and surface faults