Handwriting recognition systems and methods

1. A method for recognizing handwriting, the method comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein matching sub-characters of text to a model comprises:

mapping the model to character instances by curves, pairs of curves, and pairs of pairs of curves,

mapping structured models of characters composed of sub-characters; and

representing the mapped sub-characters and characters as a directed acyclic graph (DAG).

2. A method for recognizing handwriting, the method comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein determining most probable characters of the text based on the said matching comprises estimating k-best character probabilities from k-best graph search (A*) of a directed acyclic graph of alternative sub-character and character log probabilities of multiple character hypotheses.

3. A method for recognizing handwriting, the method comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model;

determining most probable characters of the text based on said matching;

initializing parameters of handwriting geometry based on approximately two characters of text in the received handwriting data; and

adapting to the strata of the current document sub-character geometry over the course of analysis of the document;

wherein individual writers have few strata and there are few strata across all writers.

4. A method for recognizing handwriting, the method comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model;

determining most probable characters of the text based on said matching; and

estimating the probability of a pair or tuple of received characters based on sub-word linguistic evidence of graphemes, syllables and subsyllables, and affixes.

5. A non-transitory computer-readable storage medium storing instructions for handwriting recognition, the instructions when executed by one or more processors causing the one or more processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein matching sub-characters of text to a model comprises:

mapping the model to character instances by curves, pairs of curves, and pairs of pairs of curves,

mapping structured models of characters composed of sub-characters; and

representing the mapped sub-characters and characters as a directed acyclic graph (DAG).

6. A non-transitory computer-readable storage medium storing instructions for handwriting recognition, the instructions when executed by one or more processors causing the one or more processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein the matching sub-characters of text to a model comprises:

estimating empirical conditional probability P(dlh) of parameter data based on hypothesis from order statistics of a parameter;

using signed functional distance that is not scalar; and

estimating non-parameterized empirical probability over stratified character and sub-character populations.

7. A non-transitory computer-readable storage medium storing instructions for handwriting recognition, the instructions when executed by one or more processors causing the one or more processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein determining most probable characters of the text based on the said matching comprises estimating k-best character probabilities from k-best graph search (A*) of a directed acyclic graph of alternative sub-character and character log probabilities of multiple character hypotheses.

8. A non-transitory computer-readable storage medium storing instructions for handwriting recognition, the instructions when executed by one or more processors causing the one or more processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model;

determining most probable characters of the text based on said matching;

initializing parameters of handwriting geometry based on approximately two characters of text in the received handwriting data; and

adapting to the strata of the current document sub-character geometry over the course of analysis of the document;

wherein individual writers have few strata and there are few strata across all writers.

9. A non-transitory computer-readable storage medium storing instructions for handwriting recognition, the instructions when executed by one or more processors causing the one or more processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model;

determining most probable characters of the text based on said matching; and

estimating the probability of a pair or tuple of received characters based on sub-word linguistic evidence of graphemes, syllables and subsyllables, and affixes.

10. A computer system for handwriting recognition, the computer system comprising: one or more computer processors; and one or more non-transitory computer-readable storage media, the storage media storing computer program instructions executable by the one or more computer processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein matching sub-characters of text to a model comprises:

mapping the model to character instances by curves, pairs of curves, and pairs of pairs of curves,

mapping structured models of characters composed of sub-characters; and

representing the mapped sub-characters and characters as a directed acyclic graph (DAG).

11. A computer system for handwriting recognition, the computer system comprising: one or more computer processors; and one or more non-transitory computer-readable storage media, the storage media storing computer program instructions executable by the one or more computer processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein the matching sub-characters of text to a model comprises:

estimating empirical conditional probability P(dlh) of parameter data based on hypothesis from order statistics of a parameter;

using signed functional distance that is not scalar; and

estimating non-parameterized empirical probability over stratified character and sub-character populations.

12. A computer system for handwriting recognition, the computer system comprising: one or more computer processors; and one or more non-transitory computer-readable storage media, the storage media storing computer program instructions executable by the one or more computer processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model; and

determining most probable characters of the text based on said matching,

wherein determining most probable characters of the text based on the said matching comprises estimating k-best character probabilities from k-best graph search (A*) of a directed acyclic graph of alternative sub-character and character log probabilities of multiple character hypotheses.

13. A computer system for handwriting recognition, the computer system comprising: one or more computer processors; and one or more non-transitory computer-readable storage media, the storage media storing computer program instructions executable by the one or more computer processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model;

determining most probable characters of the text based on said matching;

initializing parameters of handwriting geometry based on approximately two characters of text in the received handwriting data; and

adapting to the strata of the current document sub-character geometry over the course of analysis of the document;

wherein individual writers have few strata and there are few strata across all writers.

14. A computer system for handwriting recognition, the computer system comprising: one or more computer processors; and one or more non-transitory computer-readable storage media, the storage media storing computer program instructions executable by the one or more computer processors to perform steps comprising:

receiving handwriting data;

determining geometric data of text in handwriting data;

determining sub-characters of the text;

matching sub-characters of text to a model;

determining most probable characters of the text based on said matching; and

estimating the probability of a pair or tuple of received characters based on sub-word linguistic evidence of graphemes, syllables and subsyllables, and affixes.