METHOD FOR PROCESSING OPTICAL CHARACTER RECOGNIZER OUTPUT

• US 20130301920A1
• Filed: 05/14/2012
• Published: 11/14/2013
• Est. Priority Date: 05/14/2012
• Status: Active Grant

• Current Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Cancedda, Nicola, Venkatapathy, Sriram
• Granted Patent: US 8,983,211 B2
• Time in Patent Office: Days
• US Class Current: 382/182
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/12 Detection or correction of errors, e.g. by rescanning the pattern
• CPC Class Codes: G06V 30/262 using context analysis, e.g. lexical, syntactic or semantic context

Abstract

A method, a system, and a computer program product for processing the output of an OCR are disclosed. The system receives a first character sequence from the OCR. A first set of characters from the first character sequence are converted to a corresponding second set of characters to generate a second character sequence based on a look-up table and language scores.

Claims

1. A computer implemented method for processing an output of an optical character recognizer (OCR), the computer implemented method comprising:

receiving a first character sequence from the OCR; and

converting a first set of characters from the first character sequence to a corresponding second set of characters to generate a second character sequence based on a look-up table and language scores generated by a language model.

2. The computer implemented method of claim 1 further comprising scanning a document to generate an electronic document, wherein the electronic document is optically recognized by the OCR to generate the first character sequence.

3. The computer implemented method of claim 1 further comprising optically recognizing characters from an electronic document to generate the first character sequence.

4. The computer implemented method of claim 1, wherein the look-up table comprises a list of characters and corresponding one or more second characters.

5. The computer implemented method of claim 4, wherein the look-up table comprises one or more scores.

6. The computer implemented method of claim 5 further comprising determining the second set of characters for the first set of characters from the one or more second characters based on the one or more scores.

7. The computer implemented method of claim 5, wherein the one or more scores comprises a probability of using the one or more second characters for correcting a given one or more characters from the list of characters.

8. The computer implemented method of claim 1, wherein the converting comprises implanting a finite state transducer (FST) corresponding to each character of the first character sequence.

9. The computer implemented method of claim 8 further comprising assigning weights to the FST and the language model using a Minimum Error Rate Training (MERT) technique.

10. A computer implemented method for processing an output of an optical character recognizer (OCR), the computer implemented method comprising:

receiving a first character sequence from the OCR,

converting a first set of characters from the first character sequence to a corresponding second set of characters to generate a second character sequence based on one or more finite state transducers (FSTs) corresponding to each character of the first character sequence and language scores generated by a language model, wherein weights associated with the one or more FSTs and the language model are determined using a Minimum Error Rate Training (MERT) technique.

11. A computer implemented method for language translation comprising:

receiving a first character sequence from an optical character recognizer (OCR), the first character sequence being in a first language;

converting a first set of characters from the first character sequence to a corresponding second set of characters to generate a second character sequence based on a look-up table and language scores generated by a language model, wherein the second character sequence is in the first language; and

translating a first word sequence corresponding to the second character sequence to a second word sequence in a second language.

12. A system for processing an output of an optical character recognizer (OCR), the system comprising a processor coupled to a memory, the memory having stored therein one or more program modules comprising:

a conversion module configured for converting a first set of characters in a first character sequence to a corresponding second set of characters to generate a second character sequence based on a look-up table and language scores, wherein the first character sequence is received from the OCR.

13. The system of claim 12, wherein the OCR is configured for optically recognizing characters from an electronic document to generate the first character sequence.

14. The system of claim 12, wherein the look-up table comprises a list of characters and corresponding one or more second characters.

15. The system of claim 12, wherein the look-up table comprises one or more scores.

16. The system of claim 15, wherein the conversion module is configured for determining the second set of characters for the first set of characters from the one or more second characters based on the one or more scores.

17. The system of claim 15, wherein the one or more scores comprises a probability of using the one or more second characters for correcting a given one or more characters from the list of characters.

18. The system of claim 12 wherein, the conversion module is configured for converting the first set of characters to the second set of characters based on a cost, wherein the cost corresponds to a value indicating a likelihood of the first set of characters from the first character sequence being the second set of characters.

19. The system of claim 12 further comprising a language model configured for calculating the language scores.

20. A system for language translation, the system comprising a processor coupled to a memory, the memory having stored therein one or more program modules comprising:

a conversion module configured for converting a first set of characters in a first character sequence to a corresponding second set of characters to generate a second character sequence based on a look-up table and language scores generated by a language model, the first character sequence being received from an Optical Character Recognizer (OCR), wherein the first character sequence and the second character sequence are in a first language; and

a translation module configured for translating a first word sequence corresponding to the second character sequence to a second word sequence in a second language.