StrCombo: combination of string recognizers
Pattern Recognition Letters - In memory of Professor E.S. Gelsema
Multiple Classifier Combination Methodologies for Different Output Levels
MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
A New Evaluation Method for Expert Combination in Multi-expert System Designing
MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Evaluation of the Information-Theoretic Construction of Multiple Classifier Systems
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Selection of Classifiers for the Construction of Multiple Classifier Systems
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
MCS'03 Proceedings of the 4th international conference on Multiple classifier systems
Combination methodologies of multi-agent hyper surface classifiers: design and implementation issues
AIS-ADM'07 Proceedings of the 2nd international conference on Autonomous intelligent systems: agents and data mining
Selection of classifiers using information-theoretic criteria
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
Information-Theoretic selection of classifiers for building multiple classifier systems
ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part I
Hi-index | 0.00 |
In order to raise a class discrimination power by combining multiple classifiers, the upper bound of a Bayes error rate bounded by the conditional entropy of a class variable and decision variables should be minimized. Wang and Wong proposed a tree dependence approximation scheme of a high order probability distribution composed of those variables, based on minimizing the upper bound.In addition to that, this paper presents an extended approximation scheme dealing with higher order dependency. Multiple classifiers recognizing unconstrained handwritten numerals were combined by the proposed approximation scheme based on the minimization of the Bayes error rate, and the high recognition rates were obtained by them.