Handwritten Digit Recognition Using Classifier Cooperation Schemes
Dusan Cakmakov, Dejan Gorgevik
Abstract: Recent results in pattern recognition applications have shown that SVMs (Support Vector Machines) often have superior recognition rates in comparison to other classification methods. In this paper, the cooperation of three SVM classifiers for handwritten digit recognition, each using different feature family is examined. We investigate the advantages and weaknesses of various cooperation schemes based on classifier decision fusion using statistical reasoning. Although most of the used schemes are variations and adaptations of existing ones, such an extensive number of cooperation schemes have not been presented in the literature until now. The obtained results show that it is difficult to exceed the recognition rate of a single, well-tuned SVM classifier applied straightforwardly on all feature families as a single set. However, the classifier cooperation reduces the classifier complexity and need for samples, decreases classifier training time and sometimes improves the classifier performance.