New training strategies for RBF neural networks for X-ray agricultural product inspection |
| |
Authors: | David CasasentAuthor Vitae Xue-wen ChenAuthor Vitae |
| |
Affiliation: | Department of Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA |
| |
Abstract: | Classification of real-time X-ray images of pistachio nuts is discussed. The goal is to reduce the percentage of infested nuts while not rejecting more than a few percent of the good nuts. Radial basis function (RBF) neural network classifiers are emphasized. New training procedures are developed that allow samples such as those that are near decision boundaries to be treated differently from other samples. New clustering methods and new cluster classes are advanced to select and separately control various RBF parameters. These advancements are shown to be of use in this application. |
| |
Keywords: | Classification Clustering Discrimination Feature extraction Neural networks Product inspection Radial basis functions X-ray sensors |
本文献已被 ScienceDirect 等数据库收录! |