DocumentCode
327667
Title
A pretopology-based supervised pattern classifier
Author
Frelicot, Carl ; Lebourgeois, Franck
Author_Institution
Lab. Inf. et Imagerie Ind., Univ. de La Rochelle, France
Volume
1
fYear
1998
fDate
16-20 Aug 1998
Firstpage
106
Abstract
Deals with the pretopological approach to the supervised pattern classification problem. An improved learning process which results in a reduced number of neighborhoods to be learned is proposed. We also present extensions concerning the use of different metrics in the ∈-neighborhood definition in order to improve the class boundaries. Performances in terms of storage requirements, computation time and misclassification are provided and compared with the 1-nearest neighbor rule
Keywords
pattern classification; set theory; ∈-neighborhood definition; 1-nearest neighbor rule; class boundaries; computation time; learning process; misclassification; pretopology-based supervised pattern classifier; storage requirements; Adhesives; Ear; Neural networks; Reconnaissance;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on
Conference_Location
Brisbane, Qld.
ISSN
1051-4651
Print_ISBN
0-8186-8512-3
Type
conf
DOI
10.1109/ICPR.1998.711091
Filename
711091
Link To Document