Image segmentation for data verification

• US 9,519,404 B2
• Filed: 05/15/2015
• Issued: 12/13/2016
• Est. Priority Date: 01/27/2015
• Status: Expired due to Fees

• Current Assignee: ABBYY Production LLC (ABBYY Software)
• Original Assignee: ABBYY Development LLC
• Inventors: Kanivets, Diana
• Primary Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US14/713,260
• Publication Number:
  US 20160216851A1
• Time in Patent Office: 578 Days
• Field of Search: 382/173, 382/177
• US Class Current: 1/1
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• CPC Class Codes: G06T 2200/24 involving graphical user interfaces [GUIs]
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks
• CPC Class Codes: G06V 30/412 Layout analysis of documents structured with printed lines or input boxes, e.g. business forms or tables

Abstract

Aspects of the present disclosure relate to image segmentation for data verification. A method of the disclosure comprises: receiving, using a processing device, an image of at least a part of a document; identifying a first image region in the image that corresponds to data to be verified by a user; extracting data from the image of at least the part of the document partitioning the image into a plurality of image segments based on positioning information related to the first image region, wherein the plurality of image segments comprises a first image segment and a second image segment, and wherein the second image segment comprises the first image region; and presenting data extracted from the first image region in association with the first image segment and the second image segment.

Claims

1. A method, comprising:

receiving, using a processing device, an image of at least a part of a document;

extracting data from the image of at least the part of the document;

identifying a first image region in the image that corresponds to the extracted data to be verified by a user;

partitioning the image into a plurality of image segments based on positioning information related to the first image region, wherein the plurality of image segments comprises a first image segment and a second image segment, and wherein the second image segment comprises the first image region; and

presenting data extracted from the first image region in association with the first image segment and the second image segment in a user interface.

2. The method of claim 1, wherein presenting the data extracted from the first image region comprises presenting a first value of the data extracted from the first image region in a first display field in the user interface, wherein the first display field is positioned between the first image segment and the second image segment in the user interface.

3. The method of claim 2, wherein the first display field does not overlap the second image segment presented in the user interface.

4. The method of claim 2, wherein the first image segment does not overlap the second image segment.

5. The method of claim 2, further comprising:

identifying a plurality of image regions corresponding to the extracted data to be verified by the user, wherein the plurality of image regions comprises the first image region; and

presenting data extracted from the plurality of image regions in a plurality of display fields in the user interface, wherein the plurality of display fields comprises the first display field, wherein each of the plurality of display fields is positioned above one of the image regions in the user interface.

6. The method of claim 5, wherein the display fields do not overlap the first image segment or the second image segment presented in the user interface.

7. The method of claim 1, wherein partitioning the image into the plurality of segments comprises:

generating a plurality of slicing lines; and

partitioning the image into the plurality of image segments based on the plurality of slicing lines.

8. The method of claim 7, wherein the plurality of slicing lines comprises a first slicing line that is parallel to a first direction and a second slicing line that is parallel to a second direction.

9. The method of claim 8, wherein the first direction is perpendicular to the second direction.

10. The method of claim 8, further comprising generating the first slicing line based on the positioning information related to the first image region.

11. The method of claim 8, further comprising:

identifying a first dividing line in the image; and

generating the second slicing line based on positioning information related to the first dividing line, wherein the first dividing line is parallel to the second direction.

12. The method of claim 11, further comprising:

identifying a second dividing line in the image; and

generating a third slicing line based on positioning information related to the second dividing line, wherein the second dividing line is parallel to the first direction.

13. The method of claim 8, further comprising:

identifying a second image region in the image that corresponds to the extracted data to be verified; and

generating a fourth slicing line parallel to the first direction based on positioning information related to the second image region, wherein the second image segment comprises the second image region.

14. The method of claim 13, further comprising generating a fifth slicing line parallel to the second direction based on the positioning information related to the second image region.

15. The method of claim 13, further comprising presenting a second value of data extracted from the second image region in a second display field of the user interface, wherein the second display field is positioned between the first image segment and the second image segment in the user interface.

16. The method of claim 1, wherein identifying the first image region comprises determining at least one of a confidence score or an error related to the data extracted from the first image region.

17. A system, comprising:

a memory; and

a processing device communicably coupled to the memory to;

receive an image of at least a part of a document;

extract data from the image of at least the part of the document;

identify a first image region in the image that corresponds to the extracted data to be verified by a user;

partition the image into a plurality of image segments based on positioning information related to the first image region, wherein the plurality of image segments comprises a first image segment and a second image segment, and wherein the second image segment comprises the first image region; and

present data extracted from the first image region in association with the first image segment and the second image segment in a user interface.

18. The system of claim 17, wherein to present the data extracted from the first image region, the processing device is further to present a first value of the data extracted from the first image region in a first display field of the user interface, wherein the first display field is positioned between the first image segment and the second image segment in the user interface.

19. The system of claim 18, wherein the first display field does not overlap the second image segment presented in the user interface.

20. A non-transitory machine-readable storage medium including instructions that, when accessed by a processing device, cause the processing device to perform operations comprising:

receiving, using the processing device, an image of at least a part of a document;

extract data from the image of at least the part of the document;

identifying a first image region in the image that corresponds to the extracted data to be verified by a user;

partitioning the image into a plurality of image segments based on positioning information related to the first image region, wherein the plurality of image segments comprises a first image segment and a second image segment, and wherein the second image segment comprises the first image region; and

presenting data extracted from the first image region in association with the first segment and the second segment in a user interface.