DocumentCode
2787260
Title
A comparison of rule-based, k -nearest neighbor, and neural net classifiers for automated industrial inspection
Author
Cho, Tai-Hoon ; Conners, R.W. ; Araman, Philip A.
Author_Institution
Virginia Polytech. Inst. & State Univ., Blacksburg, VA, USA
fYear
1991
fDate
30 Sep-2 Oct 1991
Firstpage
202
Lastpage
209
Abstract
As classifiers for use in automated industrial inspection, the rule-based, k -nearest-neighbor, and neural-network approaches are discussed. These approaches were implemented and tested for label verification in a machine vision system for hardwood lumber inspection. The test results, together with other considerations, have led to the selection of neural networks as the preferred method for doing the label verification in this machine vision system
Keywords
automatic optical inspection; computer vision; computerised pattern recognition; industrial computer control; knowledge based systems; neural nets; automated industrial inspection; hardwood lumber inspection; k-nearest neighbor; label verification; machine vision; neural net classifiers; rule-based; Data analysis; Data mining; Focusing; Image segmentation; Inspection; Labeling; Machine vision; Neural networks; Performance evaluation; Testing;
fLanguage
English
Publisher
ieee
Conference_Titel
Developing and Managing Expert System Programs, 1991., Proceedings of the IEEE/ACM International Conference on
Conference_Location
Washington, DC
Print_ISBN
0-8186-2250-4
Type
conf
DOI
10.1109/DMESP.1991.171738
Filename
171738
Link To Document