Biomimetic segmentation of unconstrained touching numeral strings

This paper presents a new bionic segmentation method which chooses principal curves to extract strokes of characters and form the stroke sequence. The training sample space is constructed by the Affinity Propagation (AP) algorithm and Bionic Pattern Recognition (BPR) theory. The stroke sequence is divided by calculating the distance of each subsequence to the relative subspace. Experimental results indicate that the method is effective in the segmentation of unconstrained handwritten numeral strings.