In this paper, we present a method that functionally combines a convolutional neural network (CNN) and a support vector machine (SVM) to classify defects occurring on the inner surface of an automobile tire. Because such defects are usually small, the image requires high resolution to show the shape change of the defect in the image. Dividing one image into multiple images of smaller regions increases the number of images, which limits the applicable machine learning methods. For this reason, CNN is applied to the divided images of the whole tire, while SVM is applied to the divided images within the range delimited by CNN. Experimental results demonstrate that the defect detection rate of the proposed method is 100%, with an area rate of over-detection of 0.040% in the inspection range of a non-defective tire, demonstrating that the method is effective for reducing over-detection errors while maintaining defect detection accuracy.
This paper proposes a scheme for embedding patterns onto the Hyperbolic-valued Hopfield Neural Networks (HHNNs). This scheme is based on gradient descent learning (GDL), in which the connection weights among neurons are gradually modified by iterative applications of patterns to be embedded. The performances of the proposed scheme are evaluated though several types of numerical experiments, as compared to projection rule (PR) for HHNNs. Experimental results show that pattern embedding by the proposed GDL is still possible for large number of patterns, in which the embedding by PR often fails. It is also shown that the proposed GDL can be improved, in terms both of stability of embedded patterns and of computational costs, by configuring the initial connection weights by PR and then by modifying the connection weights by GDL.