Method and system for character recognition

1. An article of manufacture comprising a non-transitory computer-readable medium with instructions encoded thereon, the instructions configured to cause one or more processors to perform a method comprising:

receiving an image of a sequence of glyphs;

for each of a subset of glyphs of the sequence:

determining whether the glyph matches a retained glyph;

assigning to the glyph a character identity associated with the retained glyph in response to determining that the glyph matches a retained glyph;

retaining the unmatched glyph, selecting a character identity for the unmatched glyph, and assigning the selected character identity to the unmatched glyph in response to determining that the glyph does not match a retained glyph;

generating a representation of the image of the sequence of glyphs with the assigned character identities; and

identifying the sequence of glyphs using the generated representation.

2. The article of manufacture of claim 1 , wherein the assigned character identities relate to a spatial or ordinal position of the glyph within the sequence of glyphs.

3. The article of manufacture of claim 1 , wherein identifying the sequence of glyphs using the generated representation includes identifying a single sequence of glyphs from multiple possible sequences of glyphs represented by the generated representation by comparing shape information associated with the generated representation to shape information associated with the identified multiple possible sequences of glyphs.

4. The article of manufacture of claim 1 , wherein determining whether a glyph matches a retained glyph includes determining that the glyph matches a retained glyph to a certain degree of probability.

5. The article of manufacture of claim 1 , wherein retaining the glyph includes adding an image of the glyph to a template of glyph images.

6. A method comprising:

storing an image of a text sequence in a non-transitory computer-readable medium associated with a computing system, the text sequence including multiple glyphs unknown to the computing system;

using one or more processors associated with the computing system to associate an identity to a subset of the multiple glyphs based on (1) similarities in shape between the glyphs within the image of the text sequence, and (2) relative locations of the glyphs within the image of the text sequence; and

using the one or more processors to generate a text representation by replacing the glyphs with the associated identities.

7. The method of claim 6 , further comprising:

using the one or more processors to compare the generated text representation with a database of text representations to recognize the text sequence represented by the generated text representation.

8. The method of claim 6 , further comprising:

using the one or more processors to compare the generated text representation with a database of text representations to identify two or more candidate text representations that match the generated text representation; and

using the one or more processors to query a dictionary to assign probabilities to the candidate text representations, where the assigned probabilities are based on a relative linguistic likelihood of the candidate text representation.

9. The method of claim 6 , further comprising:

using the one or more processors to compare the generated text representation with a database of text representations to identify two or more candidate text representations that match the generated text representation; and

using the one or more processors to compare shape information associated with the generated text representation to shape information associated with the candidate text representations.

10. An article of manufacture comprising a non-transitory computer-readable medium with instructions encoded thereon, the instructions configured to cause one or more processors associated with a computing system to perform a method comprising:

receiving an image of a text sequence, the text sequence including multiple glyphs unknown to the computing system;

associating an identity to a subset of the multiple glyphs based on (1) similarities in shape between the glyphs within the image of the text sequence, and (2) relative locations of the glyphs within the image of the text sequence; and

generating a text representation by replacing the glyphs with the associated identities.

11. A method comprising:

storing an image of a sequence of glyphs in a non-transitory computer-readable medium associated with one or more processors;

for each of at least a subset of the glyphs, in the order of the sequence:

determining whether an identifier has been attributed to the glyph;

in response to determining that no identifier has been attributed to the glyph:

selecting an unassigned identifier;

assigning the selected identifier to the glyph;

attributing the selected identifier to the glyph; and

attributing the selected identifier to any glyphs that follow the glyph in the sequence and match the glyph; and

generating an encoding of the image that is based on the identifiers attributed to the glyphs of the sequence.

12. The method of claim 11 , wherein the generating includes concatenating the identifiers attributed to the glyphs in the order of the sequence.

13. The method of claim 11 , wherein the generating includes generating an encoding that contains, for glyphs to which the same identifier was attributed, the same value.

14. The method of claim 11 , wherein the generating includes generating an encoding that contains, for each of at least a subset of the glyphs, an offset in the sequence to a glyph to which the same identifier was attributed.

15. An article of manufacture comprising a non-transitory computer-readable medium with instructions encoded thereon, the instructions configured to cause one or more processors to perform a method comprising:

receiving an image of a sequence of glyphs;

initializing an encoding of the image;

for each of at least a subset of the glyphs, in the order of the sequence:

determining an offset to a glyph earlier in the sequence that matches the glyph; and

storing a value in the encoding that indicates the determined offset.

16. The article of manufacture of claim 15 wherein the determining includes determining an offset to the earliest glyph in the sequence that matches the glyph.

17. The article of manufacture of claim 15 wherein the determining includes determining an offset to the most recent glyph in the sequence that matches the glyph.

18. A method comprising:

storing an image of a sequence of glyphs in a non-transitory computer-readable medium associated with one or more processors;

using the one or more processors to initialize an encoding of the image; and

for each of at least a subset of the glyphs, in the order of the sequence, using the one or more processors to determine an offset to a glyph earlier in the sequence that matches the glyph and store an indication of the determined offset in the encoding.