Method of identifying pattern training need during verification of recognized text

1. A computer-implemented method for text analysis, comprising:

analyzing verification performed by a user on a recognized text obtained by character recognition of a document image,

wherein the verification comprises changing an incorrect character identified by the user for a correct character identified by the user;

identifying analogous changes of a first incorrect character for a first correct character; and

initiating a training of a recognition pattern based on the identified analogous changes,

wherein the recognition pattern is a pattern used in character recognition of the document image to generate the recognized text.

2. The computer-implemented method of claim 1 , wherein:

the identifying analogous changes comprises

tracking a number of analogous changes of the first incorrect character for the first correct character during the verification, and

determining that the number of analogous changes of the first incorrect character for the first correct character has reached a predetermined threshold, and

the initiating of the training of the recognition pattern is based on the determining that the number of analogous changes has reached the predetermined threshold.

3. The computer-implemented method of claim 1 , wherein the initiating the training of the recognition pattern comprises presenting the user with an option to initiate the training.

4. The computer-implemented method of claim 1 , wherein the initiating the training of the recognition pattern is automatic.

5. The computer-implemented method of claim 1 , further comprising

repeating character recognition of the document image based on the trained recognition pattern.

6. The computer-implemented method of claim 1 , further comprising

repeating character recognition of an unverified portion of the document image based on the trained recognition pattern.

7. The method of claim 1 , wherein identifying analogous changes of a first incorrect character for a first correct character comprises automatically tracking analogous changes during verification of recognition results.

8. Computer storage media encoded with one or more computer programs, the one or more computer programs comprising instructions that when executed by a data processing apparatus cause the data processing apparatus to perform operations comprising:

analyzing verification performed by a user on a recognized text obtained by character recognition of a document image,

wherein the verification comprises changing an incorrect character identified by the user for a correct character identified by the user;

identifying analogous changes of a first incorrect character for a first correct character; and

initiating a training of a recognition pattern based on the identified analogous changes, wherein the recognition pattern is a pattern used in character recognition of the document image to generate the recognized text.

9. The computer storage media of claim 8 , wherein:

the identifying analogous changes comprises

tracking a number of analogous changes of the first incorrect character for the first correct character during the verification, and

determining that the number of analogous changes of the first incorrect character for the first correct character has reached a predetermined threshold, and

the initiating of the training of the recognition pattern is based the determining that the number of analogous changes has reached the predetermined threshold.

10. The computer storage media of claim 8 , wherein the initiating the training of the recognition pattern comprises presenting the user with an option to initiate the training.

11. The computer storage media of claim 8 , wherein the initiating the training of the recognition pattern is automatic.

12. The computer storage media of claim 8 , further comprising

repeating character recognition of the document image based on the trained recognition pattern.

13. The computer storage media of claim 8 , further comprising

repeating character recognition of an unverified portion of the document image based on the trained recognition pattern.

14. A system, comprising:

a computing device; and

a computer-readable medium coupled to the computing device and having instructions stored thereon which, when executed by the computing device, cause the computing device to perform operations comprising:

analyzing verification performed by a user on a recognized text obtained by character recognition of a document image,

wherein the verification comprises changing an incorrect character identified by the user for a correct character identified by the user;

identifying analogous changes of a first incorrect character for a first correct character; and

initiating a training of a recognition pattern based on the identified analogous changes,

wherein the recognition pattern is a pattern used in character recognition of the document image to generate the recognized text.

15. The system of claim 14 wherein:

the identifying analogous changes comprises

tracking a number of analogous changes of the first incorrect character for the first correct character during the verification, and

determining that the number of analogous changes of the first incorrect character for the first correct character has reached a predetermined threshold, and

the initiating of the training of the recognition pattern is based the determining that the number of analogous changes has reached the predetermined threshold.

16. The system of claim 14 , wherein the initiating the training of the recognition pattern comprises presenting the user with an option to initiate the training.

17. The system of claim 14 , wherein the initiating the training of the recognition pattern is automatic.

18. The system of claim 14 , further comprising

repeating character recognition of the document image based on the trained recognition pattern.

19. The system of claim 14 , further comprising

repeating character recognition of an unverified portion of the document image based on the trained recognition pattern.