Image text to character information conversion

• US 8,155,444 B2
• Filed: 01/15/2007
• Issued: 04/10/2012
• Est. Priority Date: 01/15/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Simmons, Alex J., Nickolov, Radoslav P., Baer, Peter, Lascaux, Vincent, Kofman, Igor
• Primary Examiner(s): Zarka, David
• Application Number:
  US11/623,184
• Publication Number:
  US 20080170785A1
• Time in Patent Office: 1,912 Days
• Field of Search: 382/176
• US Class Current: 382/176
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1456 based on user interactions

Abstract

Converting text may be provided. A user selectable element may be used to select a text. The selected text may include a first text within an electronic document and a second text within an image. The second text within the image may be converted to character information by receiving the image. The image may have image character information and an image type. An aspect of the received image may be adjusted based on the image type. Optical character recognition may be performed on the adjusted image to extract character information. The character information may include characters and corresponding location information for the characters. The extracted character information may be evaluated to improve the recognition quality of the extracted character information as compared to the image character information.

Claims

1. A method for converting text, the method comprising:

selecting, with a user selectable element, a selection text comprising a first text within an electronic document and a second text within an image located in the electronic document; and

converting, by a computer, in response to selecting the selection text, the second text within the image to character information, wherein converting the second text within the image to the character information comprises;

receiving the image having an image type and image character information;

adjusting an aspect of the received image based on the image type;

performing optical character recognition on the adjusted image to extract the character information comprising characters and corresponding location information for the characters on the adjusted image, the location information comprising at least one of the following;

a page number, a line number, a paragraph number, a pixel location, and a coordinate within a plane; and

evaluating the extracted character information to improve recognition quality of the extracted character information as compared to the second text; and

pasting the selection text into another electronic document.

2. The method of claim 1, wherein evaluating the extracted character information to improve the recognition quality of the extracted word information as compared to received character information further comprises assigning a confidence level to the extracted word and interpret the confidence level to determine if the extracted word matches a dictionary word.

3. The method of claim 1, wherein adjusting the aspect of the received image based on the image type further comprises adjusting the aspect of the received image based on the image type comprising padding the received image to create a boundary around the received image.

4. The method of claim 1, wherein adjusting the aspect of the received image based on the image type further comprises removing at least one proofing mark from the received image.

5. The method of claim 1, wherein adjusting the aspect of the received image based on the image type further comprises performing a light adjustment on the received image.

6. A computer-readable storage medium device that stores a set of instructions, which when executed performs a method for converting text, the method executed by the set of instructions comprising:

selecting, with a user selectable element, a selection text comprising a first text within an electronic document and a second text within an image located in the electronic document; and

converting, in response to selecting the selection text, the second text within the image to character information, wherein converting the second text within the image to the character information comprises;

receiving the image having an image type and image character information;

adjusting an aspect of the received image based on the image type;

performing optical character recognition on the adjusted image to extract the character information comprising characters and corresponding location information for the characters on the adjusted image, the location information comprising at least one of the following;

a page number, a line number, a paragraph number, a pixel location, and a coordinate within a plane; and

evaluating the extracted character information to improve recognition quality of the extracted character information as compared to the second text; and

pasting the selection text into another electronic document.

7. The computer-readable medium of claim 6, wherein evaluating the extracted character information to improve the recognition quality of the extracted word information as compared to received character information further comprises assigning a confidence level to the extracted word and interpret the confidence level to determine if the extracted word matches a dictionary word.

8. The computer-readable medium of claim 6, wherein adjusting the aspect of the received image based on the image type further comprises adjusting the aspect of the received image based on the image type comprising padding the received image to create a boundary around the received image.

9. The computer-readable medium of claim 6, wherein adjusting the aspect of the received image based on the image type further comprises removing at least one proofing mark from the received image.

10. The computer-readable medium of claim 6, wherein adjusting the aspect of the received image based on the image type further comprises performing a light adjustment on the received image.

11. A system for converting text, the system comprising:

a memory storage; and

a processing unit coupled to the memory storage, wherein the processing unit is operative to;

select, with a user selectable element, a selection text comprising a first text within an electronic document and a second text within an image located in the electronic document; and

convert in response to selecting the selection text, the second text within the image to character information, wherein the processing unit being operative to convert the second text within the image to the character information comprises the processing unit being operative to;

receive the image having an image type and image character information;

adjust an aspect of the received image based on the image type;

perform optical character recognition on the adjusted image to extract the character information comprising characters and corresponding location information for the characters on the adjusted image, the location information comprising at least one of the following;

a page number, a line number, a paragraph number, a pixel location, and a coordinate within a plane; and

evaluate the extracted character information to improve recognition quality of the extracted character information as compared to the second text; and

paste the selection text into another electronic document.

12. The system of claim 11, wherein the processing unit being operative to evaluate the extracted character information to improve the recognition quality of the extracted word information as compared to received character information further comprises the processing unit being operative to assign a confidence level to the extracted word and interpret the confidence level to determine if the extracted word matches a dictionary word.

13. The system of claim 11, wherein the processing unit being operative to adjust the aspect of the received image based on the image type further comprises the processing unit being operative to adjust the aspect of the received image based on the image type comprises the processing unit being operative to padding the received image to create a boundary around the received image.

14. The system of claim 11, wherein the processing unit being operative to adjust the aspect of the received image based on the image type further comprises the processing unit being operative to remove at least one proofing mark from the received image.

15. The system of claim 11, wherein the processing unit being operative to adjust the aspect of the received image based on the image type further comprises the processing unit being operative to perform a light adjustment on the received image.