The segmentation algorithm for handwritten numeral strings in bank-check recognition

Abstract

In this paper, an integrated system of segmenting unconstrained handwritten numeral strings with unknowing number of digits is proposed, which consists of the extraction of connected components based on vertical projection and isolated components analysis, the length estimation of connected components using syntax analysis and waveform analysis and the segmentation of unconstrained connected handwritten numeral strings using innovative reverse drop-falling  algorithm. This segmentation system which has promising results is then incorporated into a complete bank check character recognition system.