A Hybrid Approach for Segmentation on Handwritten Numeral Strings in Form Document

摘要

This paper presents a hybrid approach lo segment single- or multiple-touching handwritten numeral strings in form document, the core of which is the combined use of foreground, background and recognition analysis. The algorithm firs! located some feature points on both the foreground and background skeleton images containing connected numeral strings in form document Possible segmentation paths were then constructed by matching these feature points, with an unexpected bonus of removing useless strokes. Subsequently, all these segmentation paths were validated and ranked by a recognition-based analysis. To do this, a well-trained two-stage classifier was applied to each separated digit image to obtain its reliability. Finally, by intro ducing a locally optimal strategy to accelerate the recognition process, the lop ranked segmentation path survived to help make a decision on whether to accept or not. Experimental results show that this hybrid approach can achieve a correct segmentation rate of 96.2 percent on a large dataset collected by our own.