Passive embedded interaction code

• US 20040086191A1
• Filed: 10/31/2002
• Published: 05/06/2004
• 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 7,133,563 B2
• Time in Patent Office: Days
• US Class Current: 382/240
• 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 system for encoding an image of a document comprising:

an input that receives said image of said document;

a parser that parses said image into sub-images;

a encoder that encodes said sub-images into a code;

a storage that stores said code associated with a location of said sub-images in relation to said image.

2. The system for encoding according to claim 1, wherein said encoder encodes based on sections of said sub-images.

3. The system for encoding according to claim 1, wherein said encoder encodes based on radial analysis of said sub-images.

4. A system for creating a codebook comprising:

an input that receives codes associated with sub-images of an image;

a processor that organizes said codes into said codebook, said codes being associated with a location of said sub-images in relation to said image; and

a storage that stores said code book.

5. The system for creating a codebook according to claim 4, wherein said processor organizes said codes into a linear list of said codes.

6. The system for creating a code book according to claim 4, wherein said processor organizes said codes into a binary tree.

7. The system for creating a code book according to claim 6, wherein said binary tree separates said codes based on their distance from a centroid of said code book.

8. The system for creating a code book according to claim 7, wherein said binary tree further separates said codes based on their distance from centroid'"'"'s of subsections of said code book

9. A system for searching a code book comprising:

a first input that receives a code book having codes associated with sub-images of an image and information relating to the location of the sub-images in said image;

a second input that receives an image from camera attached to a pen;

an encoder that encodes said image from said camera and output a code associated with said camera image;

a processor that searches said code book for one or more code candidates that are similar to said code associated with said camera image;

an output that outputs one or more locations associated with said one or code candidates.

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

receiving said document image;

parsing said document into sub-images;

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

11. The method for encoding information according to claim 10, further comprising the step of:

associating said sub-images with location information relating to where said sub-images are located in said document image.

12. The method for encoding information according to claim 10, further comprising the step of:

processing at least one of said sub-images, thereby creating a dataset that has less information said one of said sub-images.

13. The method for encoding information according to 10, further comprising the step of:

processing at least one of said sub-images by radial coding.

14. The method for encoding information according to claim 10 to further comprising the step of image processing said sub-images.

15. A method for creating a codebook comprising the steps of:

receiving encoded information regarding a sub-image;

receiving location information regarding where said sub-image is located in a larger image;

associating said encoded information with said location information; and

,

storing said associated information as said codebook.

16. The method according to claim 15, wherein said storing step further comprises storing said codebook as a linear list.

17. The method according to claim 15, wherein said storing step further comprises storing said codebook as a binary tree.

18. The method according to claim 17, further comprising the step of reducing the size of said encoded information for storage in said binary tree.

19. The method according to claim 17, further comprising the steps of:

finding a centroid of said encoded information;

finding a first code of said encoded information farthest from said centroid;

finding a second code of said encoded information farthest from said first code; and

separating said encoded information to two datasets, with one closer to said first code and the other closer to said second code.

20. The method according to claim 19, wherein repeating the steps of finding a centroid through separating said encoded information until a binary is realized.