Disclosed is a method of segmenting touching numeral strings contained
in handwritten touching numeral strings, and recognizing the numeral strings by
use of feature information and recognized results provided by inherent structure
of digits. The method comprises the steps of: receiving a handwritten numeral string
extracted from a pattern document; smoothing a curved numeral image of the handwritten
numeral string, and searching connecting components in the numeral image; determining
whether or not the numeral string is a touching numeral string; if it is determined
that the numeral string is the touching numeral string, searching a contour of
the touching numeral string image; searching candidate segmentation points in the
contour, and segmenting sub-images; computing a segmentation confidence value on
each segmented sub-image by use of a segmentation error function to select the
sub-image with the highest segmentation confidence value as a segmented numeral
image in the touching numeral string image; if it is determined in the step c that
the numeral string is not the touching numeral string, extracting a feature to
recognize the segmented numeral image; segmenting the numeral image selected from
the touching numeral string in the highest segmenting confidence value; and obtaining
remaining numeral string image.
