Passive embedded interaction coding

• US 20060182309A1
• Filed: 03/22/2006
• Published: 08/17/2006
• Est. Priority Date: 10/31/2002
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Dang, Yingnong, Wu, Jiang, Wang, Jian, Ma, Xiaoxu
• Granted Patent: US 7,684,618 B2
• Time in Patent Office: Days
• US Class Current: 382/100
• CPC Class Codes: G06F 3/03545 Pens or stylus
• CPC Class Codes: H04N 19/94 Vector quantisation

Abstract

A system and method for encoding a document image and finding a location based on that image are described. A document page is encoded into codes associated with various locations of the document page. The codes are assembled into a code book. Captured images may then be similarly encoded and searched against the codes in the codebook. One or more codes and associated locations may be returned, thereby providing one or more possible locations for the captured images.

Claims

1. A method for encoding information from a document image comprising steps of:

receiving a document image;

parsing the document image into sub-images; and

adding information relating to the sub-images to a codebook.

2. The method for encoding information according to claim 1, further comprising a step of associating the sub-images with location information relating to where the sub-images are located in the document image.

3. The method for encoding information according to claim 2, wherein the location information includes position-code pairs.

4. The method for encoding information according to claim 3, wherein the codebook is searchable and indexed with a property of position-code pairs.

5. The method for encoding information according to claim 1, further comprising a step of processing at least one of the sub-images, thereby creating a dataset that has less information than the at least one of the sub-images.

6. The method for encoding information according to 1, further comprising a step of processing at least one of the sub-images by radial coding.

7. The method for encoding information according to claim 6, wherein the step of processing includes sampling the at least one sub-image by rotating a vector about the center of the at least one sub-image in a counterclockwise direction.

8. The method for encoding information according to claim 7, wherein the vector is a shortest distance from the center of the at least one sub-image to a side of the at least one sub-image.

9. The method for encoding information according to claim 1, further comprising a step of image processing the sub-images.

10. The method for encoding information according to claim 1, further comprising a step of converting the document image into a binary image.

11. The method for encoding information according to claim 1, further comprising a step of applying a rule-based analysis to content of subdivisions of the sub-images.

12. The method for encoding information according to claim 11, wherein the step of applying includes determining whether three contiguous white columns exist in a subdivision.

13. A system for encoding information from a document image comprising:

an input configured to receive a document image;

a parser component configured to parse the document image into sub-images; and

a codebook configured to store information relating to the sub-images.

14. The system of claim 13, further comprising a converter component configured to convert the sub-images into a searchable form with corresponding location information relating to where the sub-images are located in the document image.

15. The system of claim 14, wherein the location information includes position-code pairs.

16. The system of claim 13, further comprising a processor component configured to process at least one sub-image by radial coding.

17. The system of claim 16, wherein the processor is configured to sample the at least one sub-image by rotating a vector about the center of the at least one sub-image in a counterclockwise direction.

18. The system of claim 17, wherein the vector is a shortest distance from the center of the at least one sub-image to a side of the at least one sub-image.

19. One or more computer readable media storing executable instructions for performing a method for encoding information from a document image, the method comprising steps of:

receiving a document image;

parsing the document image into sub-images; and

adding information relating to the sub-images to a codebook.

20. The computer readable media of claim 19, wherein the method further comprises a step of associating the sub-images with location information relating to where the sub-images are located in the document image.