OPTICAL CHARACTER RECOGNITION

• US 20160342852A1
• Filed: 01/31/2014
• Published: 11/24/2016
• Est. Priority Date: 01/31/2014
• Status: Active Grant

• Current Assignee: Longsand Limited (Open Text Corporation)
• Original Assignee: Longsand Limited (Open Text Corporation)
• Inventors: Blanchflower, Sean
• Granted Patent: US 10,176,392 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 18/25 Fusion techniques
• CPC Class Codes: G06F 18/254 of classification results, e.g. of results related to same input data
• CPC Class Codes: G06F 18/29 Graphical models, e.g. Bayesian networks
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks

Abstract

Optical character recognition is described in various implementations. In one example implementation, a method may include receiving a plurality of optical character recognition (OCR) outputs provided by a respective plurality of OCR engines, each of the plurality of OCR outputs being representative of text depicted in a portion of an electronic image. The method may also include identifying a document context associated with the electronic image, and generating an output character set by applying a character resolution model to resolve differences among the plurality of OCR outputs. The character resolution model may define a probability of character recognition accuracy for each of the plurality of OCR engines given the identified document context. The method may also include updating the character resolution model to generate an updated character resolution model such that subsequent generating of output character sets are based on the updated character resolution model.

Claims

1. A method comprising:

receiving, at a computing system, a plurality of optical character recognition (OCR) outputs provided by a respective plurality of OCR engines, each of the plurality of OCR outputs being representative of text depicted in a portion of an electronic image;

identifying, using the computing system, a document context associated with the electronic image;

generating, using the computing system, an output character set by applying a character resolution model to resolve differences among the plurality of OCR outputs, the character resolution model defining a probability of character recognition accuracy for each of the plurality of OCR engines given the identified document context; and

updating, using the computing system, the character resolution model to generate an updated character resolution model such that subsequent generating of output character sets are based on the updated character resolution model.

2. The method of claim 1, wherein the character resolution model comprises a Bayesian prior probability distribution.

3. The method of claim 2, wherein the updated character resolution model comprises a Bayesian posterior probability distribution.

4. The method of claim 1, wherein the document context associated with the electronic image comprises an image attribute associated with the image.

5. The method of claim 1, wherein the document context associated with the electronic image comprises a textual attribute associated with the text depicted in the image.

6. The method of claim 1, wherein the document context associated with the electronic image comprises a content attribute associated with content depicted in the image.

7. The method of claim 1, wherein the document context associated with the electronic image comprises an image attribute associated with the image, a textual attribute associated with the text depicted in the image, and a content attribute associated with content depicted in the image.

8. A system comprising:

a processor resource;

a document analysis module, executable on the processor resource, to identify a document context associated with an electronic image;

a conflict resolution module, executable on the processor resource, to receive a plurality of optical character recognition (OCR) outputs provided by a respective plurality of OCR engines, each of the plurality of OCR outputs being representative of text depicted in a portion of the electronic image, and to generate an output document based on a character resolution model and the plurality of OCR outputs, the character resolution model defining a probability of character recognition accuracy for each of the plurality of OCR engines given the identified document context; and

a model updater module, executable on the processor resource, to generate an updated character resolution model for subsequent use by the conflict resolution module.

9. The system of claim 8, wherein the character resolution model comprises a Bayesian prior probability distribution.

10. The system of claim 9, wherein the updated character resolution model comprises a Bayesian posterior probability distribution.

11. The system of claim 8, wherein the document context associated with the electronic image comprises an image attribute associated with the image.

12. The system of claim 8, wherein the document context associated with the electronic image comprises a textual attribute associated with the text depicted in the image.

13. The system of claim 8, wherein the document context associated with the electronic image comprises a content attribute associated with content depicted in the image.

14. The system of claim 8, wherein the document context associated with the electronic image comprises an image attribute associated with the image, a textual attribute associated with the text depicted in the image, and a content attribute associated with content depicted in the image.

15. A computer-readable storage medium storing instructions that, when executed, cause a processor resource to;

receive a plurality of optical character recognition (OCR) outputs provided by a respective plurality of OCR engines, each of the plurality of OCR outputs being representative of text depicted in a portion of an electronic image;

identify a document context associated with the electronic image;

generate an output character set by applying a character resolution model to resolve differences among the plurality of OCR outputs, the character resolution model defining a probability of character recognition accuracy for each of the plurality of OCR engines given the identified document context; and

update the character resolution model to generate an updated character resolution model such that subsequent generating of output character sets are based on the updated character resolution model.