Real time defect detection using image segmentation

The authors present in this paper the realization of a classification board, for real-time defect detection on industrial products, using image segmentation. The classification of each pixel is completed using a real-time extraction of attributes and a geometric classification method by stress polytope training, which ensures a high decision speed (100 ns per pixels) and good performances. The decision operator has been integrated in the form of a full custom circuit, and the extraction of parameters is performed using a single high density FPGA. The industrial product can be then high-level classified using the area of the defect.