Hierarchical Behavior Knowledge Space

In this paper we present a new method for fusing classifiers output for problems with a number of classes M > 2. We extend the well-known Behavior Knowledge Space method with a hierarchical approach of the different cells. We propose to add the ranking information of the classifiers output for the combination. Each cell can be divided into new sub-spaces in order to solve ambiguities. We show that this method allows a better control of the rejection, without using new classifiers for the empty cells. This method has been applied on a set of classifiers created by bagging. It has been successfully tested on handwritten character recognition allowing better-detailed results. The technique has been compared with other classical combination methods.

• Type: Conference
• Year: 2007
• Where: MCS
• Authors: Hubert Cecotti, Abdel Belaïd
• Keywords: Classical Combination Methods, Classifiers Output, Knowledge Space Method, MCS 2007, Pattern Recognition