Comparison of combination methods of Arabic handwritten word recognizers

In this paper we present some methods to combine the outputs of a set of Arabic handwritten word recognition systems to achieve a decision with a higher performance. This performance can be expressed by lower rejection rates and higher recognition rates. The used methods range from voting schemes based on results of different recognizers to a neural network decision based on normalized confidences. In addition, several threshold functions for different reject levels are tested and evaluated. Tests with a set of recognizers, which participated in the ICDAR 2007 competition, and based on a set coming from the IFN/ENITdatabase show that high recognition rate of about 95% without reject can be achieved.