An Industrial Application Towards Classification and Optimization of Multi-Class Tile Surface Defects Based on Geometric and Wavelet Features

It is possible to detect visual surface defects with software in industrial tile production and increase productivity by automating the quality control process. In this process, low error rate cost are important indicators. order eliminate negativity effect of human factor, detection has been developed an artificial intelligence-based vision environment. Spots, scratches, cracks, pore defects, which most common classified according 6 different geometric wavelet transform attributes. Firstly, environment was created. environment, a total 150 images, equal numbers from each class, were obtained on real-time line. The resulting images converted into binary preprocessing filtering. For classification, support vector machines method, performs high two-class classifications, used one versus all approach. classifications made using RBF kernel function features as classification performance, higher success achieved defect classes than features. Real-time application for these processes Python language Ubuntu operating system.