PROCESSING TECHNIQUES FOR TEXT CAPTURE FROM A RENDERED DOCUMENT

• US 20110033080A1
• Filed: 01/29/2010
• Published: 02/10/2011
• Est. Priority Date: 05/17/2004
• Status: Active Grant

• Current Assignee: Kyocera Corporation
• Original Assignee: Exbiblio BV
• Inventors: Kushler, Clifford A., Stafford-Fraser, James Q., King, Martin T., Grover, Dale L.
• Granted Patent: US 8,489,624 B2
• Time in Patent Office: Days
• US Class Current: 382/100
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06Q 30/00 Commerce
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/262 using context analysis, e.g. lexical, syntactic or semantic context
• CPC Class Codes: G06V 30/40 Document-oriented image-based pattern recognition

Abstract

A facility for initiating a purchase is described. The facility receives a text sequence captured by a user from a rendered document using a handheld text capture device. The facility identifies in the received text sequence a reference to a distinguished product. In response to identifying the reference, the facility presents to the user an opportunity to place an order for the established product. If the user accepts the presented opportunity to order the distinct product, the facility orders the distinct product on behalf of the user.

Claims

1-13. -13. (canceled)

14. A method in a computing system for document identification, comprising:

receiving a first text sequence captured by a user from a first rendered document using a handheld text capture device;

using explicit context information to identify among a corpus of documents a first proper subset of documents from which the first text sequence capture could have been performed;

identifying a first document among the first proper subset of documents from which the first text sequence capture was performed;

receiving a second text sequence captured by a user from a second rendered document using a handheld text capture device;

using implicit context information to identify among the corpus of documents a second proper subset of documents from which the second text sequence capture could have been performed; and

identifying a second document among the second proper subset of documents from which the second text sequence capture was performed.

15. The method of claim 14 wherein the explicit context information is a unique document identifier captured from the identified first document.

16. The method of claim 14 wherein the implicit context information is a text sequence that occurs only in the second subset of documents.

17. The method of claim 14 wherein the implicit context information is a captured watermark that occurs only in the second subset of documents.

18. The method of claim 14 wherein the implicit context information is a captured text spacing pattern that occurs only in the second subset of documents.

19. The method of claim 14 wherein the implicit context information is a captured ink color that occurs only in the second subset of documents.

20. The method of claim 14 wherein the implicit context information is a captured font that occurs only in the second subset of documents.

21. The method of claim 14 wherein the implicit context information is the elapsed amount of time between the capture of the second text sequence and the text sequence capture occurring immediately before the capture of the second text sequence.

22. The method of claim 14 wherein the implicit context information is a comparison of a font encountered in the second text sequence to a font encountered in the text sequence captured immediately before the second text sequence.

23. The method of claim 14 wherein the implicit context information is a comparison of an ink color encountered in the second text sequence to an ink color encountered in the text sequence captured immediately before the second text sequence.

24. The method of claim 14 wherein the implicit context information is a comparison of a text spacing pattern encountered in the second text sequence to a text spacing pattern encountered in the text sequence captured immediately before the second text sequence.

25. The method of claim 14 wherein the implicit context information is an assessment of the user'"'"'s reading habits.

26. The method of claim 14 wherein the implicit context information is a list of periodicals to which the user subscribes.

27. The method of claim 14 wherein the implicit context information is a measure of availability of documents among the second subset.

28. The method of claim 14 wherein the implicit context information is a measure of popularity among readers of documents among the second subset.

29. The method of claim 14 wherein the implicit context information is the user'"'"'s current physical circumstance.

30. The method of claim 14, further comprising ascribing a reliability factor to the implicit context information on which the second proper subset of documents is based.

31. A computing system for document identification, comprising:

a text sequence receiving subsystem that receives text sequences each captured by a user from a rendered document using a handheld text capture device;

an explicit context derivation subsystem that derives explicit context information relating to the capture of at least a subset of the text sequences received by the text sequence receiving subsystem;

an implicit context derivation subsystem that derives implicit context information relating to the capture of at least a subset of the text sequences received by the text sequence receiving subsystem; and

a document identification subsystem that, for each text sequence received by the text sequence receiving subsystem, identifies documents among a corpus of documents from which the text sequence could have been captured, based both upon the explicit context information derived by the explicit context duration subsystem and the implicit context information derived by the implicit context derivation subsystem.

32. A handheld text capture device, comprising:

a text capture subsystem for capturing text sequences from one or more rendered documents as directed by a user;

a memory containing at least one parametric context description that can be applied to text sequences captured by the text capture subsystem to determine context information for particular text sequences; and

a processor for applying the parametric context descriptions contained in the memory to text sequences captured by the text capture subsystem to determine context information for particular text sequences.

33-35. -35. (canceled)

36. (canceled)

37. (canceled)

38. (canceled)