Handwritten word recognition using dynamic matching with variable duration

A fast matching algorithm using dynamic programming for handwritten word recognition is presented in this paper. Variable duration for each character is defined based on the character segmentation statistics obtained during the training phase. The variable duration represents the possible ways in which a character image can be split into segments. Experimental results prove that our approach using the variable duration outperforms the method using fixed duration in terms of both accuracy and speed. Processing time for matching process increases at the rate of log(N) as lexicon size N increases. Speed of 200 msec, including image handling procedures, on a single Sparc 10 platform and recognition accuracy of 96.7% are achieved for lexicon size of 10.