We develop a new method to separate touching handwritten numeral pairs using structural analysis. The string is preprocessed with an efficient algorithm for smoothing, linearization, and detection of structural points of image contours. The structural region of the string is determined. Some left- or right-side numerals of the string are recognized. The property of each hole contour in a string is detected. The touching model of a string is determined, whether single- or double-touching. For double-touching, the touching hole contour is determined. For the two touching models, the touching point is preselected, its position is corrected, and the corresponding match touching point is found. The string is separated based on all touching points. All processing procedures are based on morphological structural analyses. We have tested our method on image samples taken from the U.S. National Institute of Science and Technology (NIST) database. We used 500 sample images to design the required models. For 3287 test samples the correct-separation rate was 97.2% for single-touching strings, and 97% for double-touching strings.
"Separation of single- and double-touching handwritten numeral strings based on structural analysis," Optical Engineering 38(3), (1 March 1999). https://doi.org/10.1117/1.602129