US 8,787,660 B1Granted

System and method for performing automatic font definition

AssigneeMatrox Electronic Systems, Ltd.

InventorsChristian Simon, Sylvain Chapleau

Life of this patent

Estimating the term…

Loading patent…

Abstract

A method of defining model characters of a font. The method includes receiving a string of characters, receiving an image that includes an occurrence of the string, identifying objects in the image, determining, for each respective object, which of the objects satisfies first criteria indicating that the respective object likely corresponds to a character in the string, determining, for each respective object satisfying the first criteria, which of the objects satisfies second criteria indicating that the respective object belongs to a sequence of objects likely to correspond to the string, and defining, for each respective object satisfying the second criteria, a model character for each character of the string based upon a corresponding object of the sequence of objects. The first criteria may include aspect ratio criterion, size criterion, or both, and the second criteria may include alignment criterion, spacing criterion contrast criterion, encompassment criterion, or combinations thereof.

Claims23

Dependent claims

A non-transitory computer readable medium encoded with a plurality of instructions that when executed by at least one processor implements a method of defining model characters of a font, the method comprising acts of:

a) receiving a first input comprising a string of characters input by a user, each character of the string having an associated range for a feature value that is derived from the shape of the character and does not vary with the size of the character;
b) receiving a second input comprising an image including an occurrence of the string of characters;
c) isolating objects in the image by grouping connected foreground pixels;
d) identifying, among the isolated objects, objects that meet a character size criterion determined adaptively based upon the image and the particular string input by the user;
e) identifying, among the identified objects, a sequence of objects corresponding to the string of characters (1) based upon a comparison of a feature value of each object of the sequence of objects and the range associated with the corresponding character of the string, and (2) by applying a string criterion, specific to the particular string input by the user, requiring that each pair of objects in the sequence of objects have compatible dimensions given the corresponding pair of characters of the string they are supposed to represent;
and
f) creating a model character of the font for each character of the string of characters based upon the corresponding object of the sequence of objects.

4 more elements

Dependencies are inferred from the claim text.