Defect detection using two-dimensional moving range filter and unanimous vote among color component classifiers

In manufacturing industries, product inspection is automated and the use of image data is increasingly being employed for defect detection. A manufacturing company in Japan produces an item and inspects the produced products by using image data. Poor inspection of products might lead to delivery of defective products to consumers: termed as consumer's risk. Contrastively, strict inspection increases production cost: termed as producer's risk. Therefore, reducing the error rate is important in product inspection. We highlighted fault points by using two-dimensional moving range filter and discriminated defect production through the unanimous vote among color component classifiers. Thus, we achieved lower error rate than the current system. This research is an empirical study of using image data in defect detection.