Word-level optimization of dynamic programming-based handwritten word recognition algorithms
Paul Gader, Wen-Tsong Chen · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1999
In the standard segmentation-based approach to lexicon- driven handwritten word recognition, character recognition algorithms are generally trained on isolated characters and individual character-class confidence scores are combined to estimate confidences in the various hypothesized identities for a word. In this paper, results from investigating alternatives to these standard methods are presented. We refer to these alternative methods as system-level optimization methods.