International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 49 - Number 12 |
Year of Publication: 2012 |
Authors: Ashoka H.n, Manjaiah D.h, Rabindranath Bera |
10.5120/7679-0980 |
Ashoka H.n, Manjaiah D.h, Rabindranath Bera . A Fuzzy Reasoning Technique for Pattern Recognition. International Journal of Computer Applications. 49, 12 ( July 2012), 19-23. DOI=10.5120/7679-0980
This paper presents a fuzzy reasoning technique for pattern classification. The binary image of a pattern is partitioned into number of overlapping and non-overlapping regions for feature extraction. A set of features extracted to represent the binary images are used in the classifier design. The knowledge base (KB) is build using the statistical information involved in the interclass region features. The unknown samples features are matched with KB and assigned a membership value by the fuzzy reasoning technique for their classification. On experimentation with the handwritten numeral data, found good classification and recognition rate.