Digital image archiving and retrieval in a mobile device system

• US 8,620,114 B2
• Filed: 07/12/2011
• Issued: 12/31/2013
• Est. Priority Date: 11/29/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Chaudhury, Krishnendu, Garg, Ashutosh, Phukan, Prasenjit, Saraf, Arvind
• Primary Examiner(s): Li, Ruiping
• Application Number:
  US13/181,263
• Publication Number:
  US 20110274373A1
• Time in Patent Office: 903 Days
• Field of Search: 382/100, 382/321, 707/104.1, 707/E17.032
• US Class Current: 382/321
• CPC Class Codes: G06F 16/5846 using extracted text
• CPC Class Codes: G06V 30/2504 Coarse or fine approaches, e.g. resolution of ambiguities or multiscale approaches

Abstract

A computer-implemented method of managing information is disclosed. The method can include receiving a message from a mobile device configured to connect to a mobile device network (the message including a digital image taken by the mobile device and including information corresponding to words), determining the words from the digital image information using optical character recognition, indexing the digital image based on the words, and storing the digital image for later retrieval of the digital image based on one or more received search terms.

Claims

1. A computer-implemented method of managing information, the method comprising:

receiving one or more messages from a mobile device configured to connect to a mobile device network, the mobile device comprising a digital camera, and the one or more messages comprising a digital image taken by the digital camera, where the digital image represents a document including information corresponding to words;

determining the words from the digital image information using optical character recognition, the determining comprising selecting between at least two dictionary based language models, according to an indication of type for the document that indicates a nature of the document, and post-processing the words in accordance with the selected dictionary based language model;

indexing the digital image based on the words; and

storing the digital image for later retrieval of the digital image based on one or more received search terms.

2. The method of claim 1, wherein the receiving comprises receiving the indication of type in the one or more messages as a user specified category for the document.

3. The method of claim 1, wherein the determining comprises assessing an aspect of the digital image to determine the indication of type for the document.

4. The method of claim 1, wherein the determining comprises performing an initial optical character recognition pass to determine the indication of type for the document.

5. The method of claim 1, further comprising:

receiving the one or more search terms; and

retrieving the digital image based on the one or more search terms.

6. The method of claim 1, wherein receiving the one or more messages comprises receiving an email message having the digital image attached;

the method further comprises adding at least one of the words, and a pre-defined label corresponding to the mobile device, to the email message; and

wherein the determining, indexing and storing are performed in an electronic mail system.

7. The method of claim 1, wherein the receiving comprises receiving at least two digital images taken of a single object in response to a single input to the digital camera, and the determining comprises performing correlative optical character recognition on the at least two digital images to find the words.

8. The method of claim 1, wherein the determining comprises pre-processing the digital image to improve the optical character recognition.

9. The method of claim 8, wherein the pre-processing comprises identifying a binarization threshold for the digital image by minimizing positional variance of left and right margins of a document represented in the digital image.

10. The method of claim 8, wherein the pre-processing comprises obtaining a gray level at a higher resolution pixel by iteratively taking a weighted combination of gray levels of neighboring pixels at a lower resolution.

11. A system comprising:

a mobile device network;

a plurality of mobile devices configured to take digital images, connect to the mobile device network, and transmit the digital images over the mobile device network, wherein the digital images represent documents having different document types;

one or more computers configured to receive the digital images from the mobile devices, select between at least two dictionary based language models according to indications of document types for the digital images, each of the indications indicating a nature of a document represented by a corresponding digital image, apply optical character recognition to extract words from the digital images, index the digital images based on the extracted words, and store the digital images for later retrieval based on received search terms.

12. The system of claim 11, wherein the one or more computers are configured to receive the indications of document types as user specified categories for the digital images.

13. The system of claim 11, wherein the one or more computers are configured to assess an aspect of the digital images to determine the indications of document types.

14. The system of claim 11, wherein the one or more computers are configured to perform an initial optical character recognition pass to determine the indications of document types.

15. The system of claim 11, wherein the one or more computers comprise a first back-end component and a second back-end component, the first back-end component configured to receive the digital images, validate the mobile devices and apply the optical character recognition, and the second back-end component configured to index the digital images and store the digital images.

16. The system of claim 15, wherein the second back-end component comprises an electronic mail system.

17. The system of claim 11, wherein the one or more computers are configured to receive the search terms, and retrieve the digital images based on the search terms.

18. The system of claim 11, wherein the one or more computers are configured to associate a pre-defined label with the digital images.

19. The system of claim 11, wherein the one or more computers are configured to identify a binarization threshold for a digital image by minimizing positional variance of left and right margins of a document represented in the digital image.

20. The system of claim 11, wherein the one or more computers are configured to obtain a gray level at a higher resolution pixel by iteratively taking a weighted combination of gray levels of neighboring pixels at a lower resolution.