On-line handwriting recognition with a neuro-fuzzy method
Sung-Bae Cho · 2002
This paper describes an efficient neuro-fuzzy method for recognizing online handwriting characters. The basic idea is to train a number of network classifiers and aggregating them with fuzzy logic. The method combines the outputs of separate networks with importance of each network, which is subjectively assigned as the nature of fuzzy logic. We demonstrate the superior performance of the presented method and compare with conventional methods like voting and averaging by thorough experiments on a difficult online handwriting recognition problem.>