A method of combining multiple experts for the recognition of unconstrained handwritten numerals
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 17 (1) , 90-94
- https://doi.org/10.1109/34.368145
Abstract
For pattern recognition, when a single classifier cannot provide a decision which is 100 percent correct, multiple classifiers should be able to achieve higher accuracy. This is because group decisions are generally better than any individual驴s. Based on this concept, a method called the 驴Behavior-Knowledge Space Method驴 was developed, which can aggregate the decisions obtained from individual classifiers and derive the best final decisions from the statistical point of view. Experiments on 46,451 samples of unconstrained handwritten numerals have shown that this method achieves very promising performances and outperforms voting, Bayesian, and Dempster-Shafer approaches.Keywords
This publication has 8 references indexed in Scilit:
- A comparison of two approaches for combining the votes of cooperating classifiersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A method of combining multiple experts for the recognition of unconstrained handwritten numeralsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1995
- Decision combination in multiple classifier systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Building a new generation of handwriting recognition systemsPattern Recognition Letters, 1993
- 11th International Conference on pattern recognition August 31–September 3, 1992 On pattern, categories, and alternate realitiesPattern Recognition Letters, 1993
- Historical review of OCR research and developmentProceedings of the IEEE, 1992
- Methods of combining multiple classifiers and their applications to handwriting recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1992
- A study on the use of belief functions for medical expert systemsJournal of Applied Statistics, 1991