Boundary defect recognition using neural networks

This research presents schemes for automated visual inspection for boundary defects and classification using neural networks. An efficient method for representing circular boundaries is proposed utilizing a curvature and circular fitting algorithm. For classification, two types of neural network modelling schemes are established. First, a multi-layer perceptron is discussed for defect classification problems. Second, a Hopfield network is modelled to be used for continuous-type variables by a minimizing energy function. Extensive tests are conducted on the casting parts, then the results of neural networks are compared with those of traditional pattern classifiers.