OFF-LINE HANDWRITTEN NUMERAL STRING RECOGNITION BY COMBINING SEGMENTATION-BASED AND SEGMENTATION-FREE METHODS

We propose an off-line system for the recognition of handwritten numer al strings. The system is built upon four main components. A presegmen tation module divides the input numeral string into independent groups of digits which are processed by a cascade of two recognition methods . The digit detection module identifies and recognizes groups containi ng isolated digits and a segmentation-free module recognizes the remai ning groups containing an arbitrary number of digits. The global decis ion module merges all results and makes an accept/reject decision. Exp erimental results on data from both the CEDAR and NIST SD3 database co mpare favorably to other published methods. (C) 1997 Pattern Recogniti on Society. Published by Elsevier Science Ltd.