Separation of single- and double-touching handwritten numeral strings

To improve overall separation and classification performance for touching handwritten numeral strings, we have to deal with double-touching problems, which occur particularly for some combinations of digits. We propose a strategy to separate single- and double-touching numerical strings. The proposed technique includes: using two-cut links to deal with double-touching problems; using weighted geometric-property measures to rank both one- and two-cut links; and using a rejection scheme to reject poor links at both ranking and recognition stages. Two-cut link pairs that join the high-curvature points in inner contour(s) to those in the external contour are considered when all one-cut links that join the upper and the lower external contours fail to separate them. All combinations of one- and two-cut links are ranked according to weighted geometric-property measures, and the top links are chosen and tested by the recognition system. Experimental results on the National Institute of Standards and Technology database show that our system for solving both single- and double-touching problems compares favorably with the other techniques tested.

[1]  Malayappan Shridhar,et al.  Context-directed segmentation algorithm for handwritten numeral strings , 1987, Image Vis. Comput..

[2]  Adam Krzyzak,et al.  Segmentation of handwritten digits using contour features , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[3]  James Westall,et al.  Vertex directed segmentation of handwritten numerals , 1993, Pattern Recognit..

[4]  Hong Yan,et al.  Connected handwritten digit separation using external boundary curvature , 1994, J. Electronic Imaging.

[5]  Mohamed Cheriet,et al.  Background region-based algorithm for the segmentation of connected digits , 1992, Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems.

[6]  Yasuaki Nakano,et al.  Segmentation methods for character recognition: from segmentation to document structure analysis , 1992, Proc. IEEE.