Automated visual inspection and classification 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 the classification schemes, two types of neural network models are established. First, a multi-layer perception is discussed for defect classification problems. Second, a Hopfield network is modeled to be used for continuous-type variables by minimizing the energy function. Extensive tests are conducted on castings, then the results of neural networks are compared with those of traditional pattern classifiers.