Techniques for retrieving documents using an image capture device

• US 20060085477A1
• Filed: 10/01/2004
• Published: 04/20/2006
• Est. Priority Date: 10/01/2004
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Piersol, Kurt, Wolff, Gregory J., Phillips, Daja
• Granted Patent: US 8,489,583 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/142 using hand-held instruments; Constructional details of the instruments
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: G06V 30/418 Document matching, e.g. of document images

Abstract

Embodiments of the present invention provide techniques for retrieving electronic documents based upon images captured using an image capture device. One or more images captured by a user using an image capture device are used to search a set of documents to retrieve one or more documents that match the search query. The one or more documents retrieved by the search may then be provided to the user or some other recipient.

Claims

1. A method of retrieving electronic documents, the method comprising:

receiving an image captured using an image capture device;

extracting contents of the image;

forming a search query based upon the extracted contents; and

searching a plurality of electronic documents to identify a first electronic document that satisfies the search query.

2. The method of claim 1 wherein:

extracting the contents of the image comprises;

using an image processing technique to extract the contents of the image; and

determining a set of text patterns from the contents; and

forming a search query comprises using one or more text patterns in the set of text patterns to form the search query.

3. The method of claim 2 wherein:

using an image processing technique to extract the contents of the image comprises using an optical character recognition technique to extract the contents of the image; and

determining the set of text patterns from the contents comprises applying a filter to the extracted contents to identify the set of text patterns.

4. The method of claim 2 wherein using the one or more text patterns in the set of text patterns to form the search query comprises conjoining the one or more text patterns in the set of text patterns to form the search query.

5. The method of claim 1 further comprising communicating the first electronic document to the image capture device.

6. The method of claim 5 wherein the image capture device is a mobile phone equipped with a camera and the first electronic document is communicated to the mobile phone via a wireless network.

7. The method of claim 1 further comprising communicating the first electronic document via an email to an electronic mailing address.

8. The method of claim 1 further comprising communicating the first electronic document to a user of the image capture device.

9. The method of claim 1 further comprising communicating the first electronic document to a recipient.

10. The method of claim 1 further comprising determining a first search engine for performing the searching, and wherein searching the plurality of electronic documents comprises searching the plurality of documents using the first search engine.

11. The method of claim 10 wherein determining the first search engine comprises:

determining a location of a user of the image capture device that captured the image; and

selecting a search engine that is located proximal to the location of the user as the first search engine.

12. The method of claim 1 wherein the image is an image of a portion of a paper document and the first electronic document is an electronic version of the paper document.

13. A method of retrieving electronic documents, the method comprising:

receiving a first image captured using an image capture device;

extracting contents of the first image;

forming a search query based upon the extracted contents of the first image;

performing a search to identify a first set of electronic documents comprising one or more electronic documents that satisfy the search query;

determining if the first set of electronic documents comprises a predefined number of electronic documents;

requesting a second image if the first set of electronic documents does not comprise the predefined number of electronic documents;

extracting contents of the second image;

forming a search query based upon the extracted contents of the second image; and

performing a search to identify a second set of electronic documents comprising one or more electronic documents that satisfy the search query based upon the extracted contents of the second image.

14. The method of claim 13 wherein the predefined number is set to one.

15. A method of retrieving electronic documents, the method comprising:

receiving a first image captured by using an image capture device;

extracting contents of the first image;

forming a search query based upon the extracted contents of the first image;

performing a search using the search query formed based upon the extracted contents of the first image;

(a) requesting another image if the search does not identify at least one electronic document;

(b) receiving another image;

(c) extracting contents of the another image;

(d) forming a search query based upon the extracted contents of the another image; and

(e) performing a search using the search query formed based upon the extracted contents of the another image;

repeating (a), (b), (c), (d), and (e) until the search identifies at least one electronic document that satisfies the search query.

16. A method of retrieving electronic documents, the method comprising:

receiving an image captured using an image capture device;

extracting a plurality of text patterns from the image using an image processing technique;

selecting a subset of text patterns from the plurality of text patterns such that the plurality of text patterns comprises at least one text pattern that is not included in the subset;

forming a search query based upon the subset of text patterns;

searching a plurality of electronic documents to identify a first electronic document that satisfies the search query.

17. The method of claim 16 wherein selecting the subset of text patterns comprises selected the subset based upon an attribute associated with each text pattern in the plurality of text patterns.

18. The method of claim 17 wherein selecting the subset comprises selecting a text pattern from the plurality of text patterns to be included in the subset based upon confidence data associated with the text pattern by the image processing technique.

19. A method of retrieving electronic documents, the method comprising:

receiving an image captured using an image capture device;

extracting a plurality of text patterns from the image using an image processing technique;

selecting a first subset of text patterns from the plurality of text patterns such that the plurality of text patterns comprises at least one text pattern that is not included in the first subset;

forming a search query based upon the first subset of text patterns;

searching a plurality of electronic documents to identify a first electronic document that satisfies the search query;

performing a search using the search query formed based upon the first subset of text patterns;

selecting a second subset of text patterns from the plurality of text patterns if the search performed using the first subset of text patterns does not identify at least one electronic document;

forming a search query based upon the second subset of text patterns; and

performing a search using the search query formed based upon the second subset of text patterns.

20. A system for retrieving electronic documents, the system comprising:

a memory configured to store an image captured device using an image capture device;

a processor coupled to the memory, the processor configured to;

extract contents of the image;

form a search query based upon the extracted contents; and

search a plurality of electronic documents to identify a first electronic document that satisfies the search query.

21. The system of claim 20 wherein:

the processor is configured to extract the contents of the image by;

using an image processing technique to extract the contents of the image; and

determining a set of text patterns from the contents; and

the processor is configured to form a search query by using one or more text patterns in the set of text patterns to form the search query.

22. The system of claim 21 wherein:

using an image processing technique to extract the contents of the image comprises using an optical character recognition technique to extract the contents of the image; and

determining the set of text patterns from the contents comprises applying a filter to the extracted contents to identify the set of text patterns.

23. The system of claim 21 wherein using the one or more text patterns in the set of text patterns to form the search query comprises conjoining the one or more text patterns in the set of text patterns to form the search query.

24. The system of claim 20 further wherein the processor is configured to communicate the first electronic document to the image capture device.

25. The system of claim 24 wherein the image capture device is a mobile phone equipped with a camera and the processor is configured to communicate the first electronic document to the mobile phone via a wireless network.

26. The system of claim 20 wherein the processor is configured to communicate the first electronic document via an email to an electronic mailing address.

27. The system of claim 20 further wherein the processor is configured to communicate the first electronic document to a user of the image capture device.

28. The system of claim 20 wherein the processor is configured to communicate the first electronic document to a recipient.

29. The system of claim 20 wherein the processor is configured to determine a first search engine for performing the searching, and to search the plurality of documents using the first search engine.

30. The system of claim 29 wherein the processor is configured to determine the first search engine by:

determining a location of a user of the image capture device that captured the image; and

selecting a search engine that is located proximal to the location of the user as the first search engine.

31. The system of claim 20 wherein the image is an image of a portion of a paper document and the first electronic document is an electronic version of the paper document.

32. A computer-readable medium storing a plurality of instructions for controlling a data processor to retrieve electronic documents, the plurality of instructions comprising:

instructions that cause the data processor to receive an image captured using an image capture device;

instructions that cause the data processor to extract contents of the image;

instructions that cause the data processor to form a search query based upon the extracted contents; and

instructions that cause the data processor to search a plurality of electronic documents to identify a first electronic document that satisfies the search query.

33. A system for retrieving electronic documents, the system comprising:

a memory configured to store a first image captured using an image capture device; and

a processor coupled to the memory, the processor configured to;

extract contents of the first image;

form a search query based upon the extracted contents of the first image;

perform a search to identify a first set of electronic documents comprising one or more electronic documents that satisfy the search query;

determine if the first set of electronic documents comprises a predefined number of electronic documents;

request a second image if the first set of electronic documents does not comprise the predefined number of electronic documents;

extract contents of the second image;

form a search query based upon the extracted contents of the second image; and

perform a search to identify a second set of electronic documents comprising one or more electronic documents that satisfy the search query based upon the extracted contents of the second image.

34. A system for retrieving electronic documents, the system comprising:

a memory configured to store a first image captured using an image capture device; and

a processor coupled to the memory, the processor configured to;

extract contents of the first image;

form a search query based upon the extracted contents of the first image;

perform a search using the search query formed based upon the extracted contents of the first image;

(a) request another image if the search does not identify at least one electronic document;

(b) receive another image;

(c) extract contents of the another image;

(d) form a search query based upon the extracted contents of the another image; and

(e) perform a search using the search query formed based upon the extracted contents of the another image;

repeat (a), (b), (c), (d), and (e) until the search identifies at least one electronic document that satisfies the search query.

35. A system for retrieving electronic documents, the system comprising:

a memory configured to store an image captured using an image capture device; and

a processor coupled to the memory, the processor configured to;

extract a plurality of text patterns from the image using an image processing technique;

select a subset of text patterns from the plurality of text patterns such that the plurality of text patterns comprises at least one text pattern that is not included in the subset;

form a search query based upon the subset of text patterns;

search a plurality of electronic documents to identify a first electronic document that satisfies the search query.

36. A system for retrieving electronic documents, the system comprising:

a memory configured to store an image captured using an image capture device; and

a processor coupled to the memory, the processor configured to;

extract a plurality of text patterns from the image using an image processing technique;

select a first subset of text patterns from the plurality of text patterns such that the plurality of text patterns comprises at least one text pattern that is not included in the first subset;

form a search query based upon the first subset of text patterns;

search a plurality of electronic documents to identify a first electronic document that satisfies the search query;

perform a search using the search query formed based upon the first subset of text patterns;

select a second subset of text patterns from the plurality of text patterns if the search performed using the first subset of text patterns does not identify at least one electronic document;

form a search query based upon the second subset of text patterns; and

perform a search using the search query formed based upon the second subset of text patterns.