DocumentCode
1556373
Title
Development of a novel image sensor and its application to analysis of automobile components
Author
Sarkodie-Gyan, Thompson ; Lam, Chun-Wah ; Campbell, Andrew W.
Author_Institution
Sch. of Sci. & Technol., Teesside Univ., Middlesbrough, UK
Volume
2
Issue
2
fYear
1997
fDate
6/1/1997 12:00:00 AM
Firstpage
144
Lastpage
150
Abstract
The authors have developed a novel image sensor for continuous conditioned monitoring of high-precision tolerances of a complex automotive product. A novel mechanooptical arrangement has been designed and validated to capture the images/silhouettes of the components as input into a neural network designed on approximate reasoning architecture. The design is extensible to handle a large number of rules, and the speed of inference is almost independent of the number of rules.
Keywords
CCD image sensors; feature extraction; feedforward neural nets; fuzzy logic; fuzzy set theory; inference mechanisms; approximate reasoning architecture; automobile components; complex automotive product; continuous conditioned monitoring; high-precision tolerances; image sensor; images/silhouettes; mechanooptical arrangement; Aluminum; Automobiles; Automotive engineering; Charge coupled devices; Holography; Image analysis; Image sensors; Lamps; Optical attenuators; Optical scattering;
fLanguage
English
Journal_Title
Mechatronics, IEEE/ASME Transactions on
Publisher
ieee
ISSN
1083-4435
Type
jour
DOI
10.1109/3516.588635
Filename
588635
Link To Document