A Comparison of Rule-Based, K-Nearest Neighbor, and Neural Net Classifiers for Automated

Abstract

Over the last few years the authors have been involved in research aimed at developing a machine vision system for locating and identifying surface defects on materials. The particular problem being studied involves locating surface defects on hardwood lumber in a species independent manner. Obviously, the accurate location and identification of defects is of paramount importance in this system. In the machine vision system that has been developed, initial hypotheses generated by bottom-up processing for defect labeling are verified using top-down processing. Thus, the label verification greatly affects the accuracy of the system. For this label verification, a rule-based approach, and a k-nearest neighbor approach, and a neural network approach have been implemented. An experimental comparison of these approaches together with other considerations have made the neural net approach the preferred choice for doing the label verification in this vision system.

Citation

Cho, Tai-Hoon; Conners, Richard W.; Araman, Philip A. 1991. A Comparison of Rule-Based, K-Nearest Neighbor, and Neural Net Classifiers for Automated. Proceedings, Developing and Managing Expert System Programs. pp. 202-209.