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 numeral strings. The system is built upon four main components. A presegmentation 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 containing isolated digits and a segmentation-free module recognizes the remaining groups containing an arbitrary number of digits. The global decision module merges all results and makes an accept/reject decision. Experimental results on data from both the CEDAR and NIST SD3 database compare favorably to other published methods.