Portable text capturing method and device therefor

• US 6,473,523 B1
• Filed: 05/04/1999
• Issued: 10/29/2002
• Est. Priority Date: 05/06/1998
• Status: Expired due to Term

• Current Assignee: Paradise IP LLC (IP Edge LLC)
• Original Assignee: Xerox Corporation (Xerox Holdings Corp.)
• Inventors: Wittner, Ben S., Bothner, Carl, Newman, William M.
• Primary Examiner(s): Boudreau, Leo
• Assistant Examiner(s): SHERALI, ISHRAT I
• Application Number:
  US09/304,659
• Time in Patent Office: 1,274 Days
• Field of Search: 382/170-171, 382/173, 382/175-177, 382/181, 382/186-187, 382/189, 382/190, 382/229, 382/289-292, 382/312-313, 382/284, 348/220-221, 348/231, 348/333.01, 348/333.02, 348/333.12, 348/219, 358/462, 358/473-474, 345/156, 345/157, 345/163
• US Class Current: 382/176
• 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 30/1444 Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields

Abstract

A portable imaging device includes a user operable pointing device that operates together with interactive segmentation functions and an OCR application for capturing and converting digitally recorded images to text. The user operable pointing device permits a user of the portable imaging device to identify a region in an image with textual content. The portable imaging device evaluates whether textual and formatting content in the segmented region can be properly analyzed by the OCR application. In addition, the portable imaging device provides a mode for translating text identified in recorded images.

Claims

1. A method for capturing text with a portable imaging device, comprising the steps of:

displaying an image recorded with an imaging unit on a viewfinder;

receiving a first user input from a shutter release button;

the first user input being adjusted using a pointing device for identifying a first position within the displayed image on the viewfinder;

recording the displayed image in a memory of the portable imaging unit;

receiving a second user input from the shutter release button;

the second user input being adjusted using the pointing device for identifying a second position within the displayed image on the viewfinder;

extracting an image segment from the image stored in the memory using the first position and the second position; and

examining the image segment to identify textual content.

2. The method according to claim 1, further comprising the step of providing a notification on the viewfinder when said examining step fails to accurately identify textual content in the image segment.

3. The method according to claim 1, further comprising the step of superimposing the textual content identified in the image segment on the image displayed on the viewfinder.

4. The method according to claim 1, wherein said extracting step extracts an image segment that represents a word of text when the first position is substantially identical to the second position.

5. The method according to claim 1, wherein said extracting step extracts an image segment having boundaries defined by the first position and the second position when the first position and the second position identify substantially different positions on the viewfinder.

6. The method according to claim 1, further comprising the step of receiving a third user input from the shutter release button;

the third user input causing the textual content identified by said examining step to be stored in the memory of the portable imaging device.

7. The method according to claim 1, further comprising the step of estimating an error rate for the textual content identified by said examining step.

8. The method according to claim 7, further comprising the step providing a warning indicator when the error rate estimated by said estimating step exceeds a threshold value.

9. The method according to claim 1, further comprising the step of translating the identified textual content from a first language to a second language.

10. The method according to claim 9, wherein the second language is selected using a global positioning system.

11. A portable imaging device, comprising:

an imaging unit for outputting a digital representation of an image viewed through a lens;

a viewfinder for displaying an image recorded with said imaging unit;

a shutter release button for outputting a first user input and a second user input;

a pointing device for adjusting the first user input and the second user input;

the first user input identifying a first position within the image displayed on said viewfinder, and the second user input identifying a second position within the image displayed on said viewfinder;

a memory for recording the image displayed on said viewfinder; and

a processor for extracting an image segment from the image stored in the memory using the first position and the second position;

said processor examining the extracted image segment to identify textual content therein.

12. The portable imaging device according to claim 11, wherein said viewfinder includes means for providing a notification when said processor fails to accurately identify textual content in the image segment.

13. The portable imaging device according to claim 11, wherein said processor superimposes textual content identified in the image segment on the image displayed on said viewfinder.

14. The portable imaging device according to claim 11, wherein said processor extracts an image segment that represents a word of text when the first position is substantially identical to the second position.

15. The portable imaging device according to claim 11, wherein said processor extracts an image segment having boundaries defined by the first position and the second position when the first position and the second position identify substantially different positions on said viewfinder.

16. The portable imaging device according to claim 11, wherein said shutter release button outputs a third user input for causing the textual content identified by said processor to be stored in said memory.

17. The portable imaging device according to claim 11, wherein said processor estimates an error rate for the textual content identified.

18. The portable imaging device according to claim 17, further comprising means for providing a warning indicator when the error rate estimated by said processor exceeds a threshold value.

19. The portable imaging device according to claim 11, wherein said processor translates identified textual content from a first language to a second language.

20. The portable imaging device according to claim 19, further comprising a global positioning system for selecting the second language.