Method and device for revising OCR data by indexing and displaying potential error locations

Patent metadata

Field	Value
Publication number	US-9760786-B2
Application number	US-201514887441-A
Country	US
Kind code	B2
Filing date	Oct 20, 2015
Priority date	Oct 20, 2015
Publication date	Sep 12, 2017
Grant date	Sep 12, 2017

Abstract

The present disclosure is directed to systems, methods, and devices that enable the revising of Optical Character Recognition (OCR) data by indexing and displaying potential error locations within the OCR data. The primary method for revising the OCR data includes a terminal device indexing, displaying, receiving editing operations for, and editing the OCR data. The terminal device is configured to revise OCR data and includes an OCR review element, which, in some embodiments, is a software stored on a non-transitory, computer-readable medium, that is executed by a processing unit to cause the terminal device to index, display, receive editing operations for, and edit the OCR data.

First claim

What is claimed is:

1. A method of revising Optical Character Recognition (OCR) data stored on a non-transitory, computer-readable medium, comprising:
indexing, by a processor on a terminal device, locations of potential errors within the OCR data,
wherein the OCR data is extracted textual information from a target image;
displaying, by the terminal device, a sentence within the target image,
wherein displaying the sentence within the target image comprises highlighting the sentence in the target image, and
wherein the sentence corresponds to a portion of the OCR data that includes at least one of the potential errors;
displaying, by the terminal device, the portion of the OCR data,
wherein the portion of the OCR data is displayed inside an editing box that overlays the target image;
receiving, from a user input device, an editing operation indicating a correction to be made to the OCR data; and
editing, by the terminal device, the OCR data in response to the editing operation.

2. The method of claim 1 , wherein indexing the locations of potential errors within the OCR data further comprises retrieving the target image with the terminal device using an image capturing unit and extracting the OCR data from the target image, and wherein the image capturing unit is embedded in the terminal device.

3. The method of claim 1 , wherein indexing the locations of potential errors within the OCR data further comprises receiving the target image from a repository and extracting the OCR data from the target image.

4. The method of claim 1 , wherein indexing the locations of potential errors within the OCR data further comprises calculating an OCR certainty level and comparing the OCR certainty level with a threshold OCR certainty level.

5. The method of claim 1 , wherein indexing the locations of potential errors further comprises specifying a character position within the OCR data denoting each location.

6. The method of claim 1 , wherein indexing locations of potential errors further comprises specifying a page number and a line number within the OCR data denoting each location.

7. The method of claim 1 , wherein displaying the portion of the OCR data further comprises determining the portion of the OCR data to display, wherein determining the portion to display further comprises displaying the locations of potential errors within the OCR data and receiving, by the terminal device, an input from the user input device, wherein the input indicates a selection of the portion from the locations of potential errors within the OCR data, wherein displaying the locations of potential errors comprises displaying one or more jump to buttons associated with the locations of the potential errors, wherein the one or more jump to buttons are displayed in a separate interface from the target image and the editing box, and wherein the input denotes a jump to one of the potential errors.

8. The method of claim 1 , wherein editing the OCR data further comprises updating a change history of all changes made to the OCR data.

9. A terminal device configured to revise Optical Character Recognition (OCR) data stored on a non-transitory, computer-readable medium, comprising:
a processor, wherein the processor is configured to execute an OCR review element,
wherein the OCR review element is stored on a non-transitory, computer-readable medium and the OCR review element is configured to index locations of potential errors within the OCR data and modify the OCR data, and
wherein the OCR data is extracted textual information from a target image;
a display,
wherein the display is configured to display a sentence within the target image,
wherein the display is configured to highlight the sentence within the target image,
wherein the sentence corresponds to a portion of the OCR data that includes at least one of the potential errors,
wherein the display is configured to display the portion of the OCR data, and
wherein displaying the portion of the OCR data comprises displaying the portion of the OCR data inside an editing box that overlays the target image; and
a user input device, wherein the user input device is configured to accept editing operations to be made to the OCR data.

10. The terminal device of claim 9 , wherein the OCR review element is further configured to perform an extraction of the OCR data from the target image.

11. The terminal device of claim 9 , wherein the OCR review element is further configured to update a change history of all changes made to the OCR data when modifying the OCR data.

12. The terminal device of claim 9 , wherein the terminal device is further configured to display the locations of potential errors within the OCR data, enable a selection of the portion of the OCR data that includes at least one of the potential errors, and display editing tools configured to assist in revision of the OCR data.

13. The terminal device of claim 9 , further comprising a network interface, wherein the network interface is configured to enable communication between the terminal device and repositories, image forming apparatuses, or other terminal devices, facilitating retrieval of the OCR data.

14. The terminal device of claim 9 , further comprising an image capturing unit configured to retrieve image data, wherein the image capturing unit is embedded in the terminal device, and wherein the image data can be processed using the OCR review element.

15. A non-transitory, computer-readable medium comprising an Optical Character Recognition (OCR) review element, wherein the OCR review element, when executed by a processor, is configured to revise OCR data in a manner comprising:
indexing locations of potential errors within the OCR data,
wherein the OCR data is extracted textual information from a target image;
displaying a sentence within the target image,
wherein displaying the sentence within the target image comprises highlighting the sentence in the target image, and
wherein the sentence corresponds to a portion of the OCR data that includes at least one of the potential errors;
displaying the portion of the OCR data,
wherein the portion of the OCR data is displayed inside an editing box that overlays the target image;
receiving an editing operation indicating a correction to be made to the OCR data; and
editing the OCR data in response to the editing operation.

16. The non-transitory, computer-readable medium of claim 15 , wherein indexing the locations of potential errors within the OCR data further comprises calculating an OCR certainty level and comparing the OCR certainty level with a threshold OCR certainty level.

17. The method of claim 1 , wherein indexing locations of potential errors within the OCR data comprises storing one or more sentence numbers within the OCR data denoting each location.

18. The method of claim 1 , further comprising displaying a sentence number in the editing box, wherein the sentence number displayed in the editing box corresponds to the sentence highlighted in the target image.

19. The method of claim 1 , further comprising displaying a location indicator, wherein the location indicator displays a sentence number corresponding to the sentence currently being displayed within the target image, and wherein the location indicator is displayed adjacent to the sentence currently being displayed within the target image.

20. The non-transitory, computer-readable medium of claim 15 , wherein indexing locations of potential errors within the OCR data comprises storing one or more s

Assignees

• Kyocera Document Solutions Inc

Inventors

• Sahagun Allan
• Matysiak Jacek Joseph

Classifications

• G06V30/147

  Determination of region of interest · CPC title

• G06V30/127

  with the intervention of an operator · CPC title

• G06F3/0481 Primary

  based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance · CPC title

• G06F40/232

  Orthographic correction, e.g. spell checking or vowelisation · CPC title

• G06F40/166

  Editing, e.g. inserting or deleting · CPC title