Detecting a label from an image

• US 8,971,620 B2
• Filed: 09/09/2013
• Issued: 03/03/2015
• Est. Priority Date: 09/21/2012
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Zhang, Lun, Chu, Rufeng, Zhang, Chunhui
• Primary Examiner(s): BEKELE, MEKONEN T
• Application Number:
  US14/021,564
• Publication Number:
  US 20140086483A1
• Time in Patent Office: 540 Days
• Field of Search: 382/170, 382/140, 382/105, 382/120, 382/201, 382/203, 382/195, 382/165
• US Class Current: 382/165
• CPC Class Codes: G06V 10/245 by locating a pattern; Special marks for positioning
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/1448 based on markings or identifiers characterising the document or the area
• CPC Class Codes: G06V 30/184 by analysing segments intersecting the pattern
• CPC Class Codes: G06V 30/224 of printed characters having additional code marks or containing code marks

Abstract

Determining a label from an image is disclosed, including: obtaining an image; determining a first portion of the image associated with a special mark; determining a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark; and applying character recognition to the second portion of the image associated with the label to determine a value associated with the label.

Claims

1. A system, comprising:

one or more processors configured to;

obtain an image;

determine a first portion of the image associated with a special mark;

determine a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark, wherein to determine the second portion of the image associated with the label based at least in part on the first portion of the image associated with the special mark includes to search for the second portion of the image associated with the label in an area of the image near a location of the first portion of the image associated with the special mark; and

apply character recognition to the second portion of the image associated with the label to determine a value associated with the label; and

one or more memories coupled to the one or more processors and configured to provide the one or more processors with instructions.

2. The system of claim 1, wherein the image is obtained based at least in part on one or more of the following:

receiving the image via a camera, receiving the image via a scanner, and downloading the image.

3. The system of claim 1, wherein the image is associated with one or more products.

4. The system of claim 3, wherein the label includes identifying information associated with the one or more products.

5. The system of claim 1, wherein to determine the first portion of the image associated with the special mark includes to:

detect in the image a shape with black boundaries associated with a special mark pattern;

compare content enclosed by the black boundaries to a designated content associated with the special mark pattern; and

in the event that the content enclosed by the black boundaries matches the designated content, determine that a portion of the image including the shape with the black boundaries comprises the first portion of the image associated with the special mark.

6. The system of claim 1, wherein to determine the first portion of the image associated with the special mark includes to:

detect in the image a shape with black boundaries associated with a special mark pattern;

determine whether a line of pixels within the black boundaries matches a black-white pixel ratio associated with the special mark pattern; and

in the event it is determined that the line of pixels within the black boundaries matches the black-white pixel ratio associated with the special mark pattern, determine that a portion of the image including the shape with the black boundaries comprises the first portion of the image associated with the special mark.

7. The system of claim 1, wherein the one or more processors are further configured, prior to applying character recognition to the second portion of the image associated with the label, to extract the second portion of the image associated with the label from the image.

8. A method, comprising:

obtaining an image;

determining, using one or more processors, a first portion of the image associated with a special mark;

determining a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark, wherein determining the second portion of the image associated with the label based at least in part on the first portion of the image associated with the special mark includes searching for the second portion of the image associated with the label in an area of the image near a location of the first portion of the image associated with the special mark; and

applying character recognition to the second portion of the image associated with the label to determine a value associated with the label.

9. The method of claim 8, wherein the image is obtained based at least in part on one or more of the following:

receiving the image via a camera, receiving the image via a scanner, and downloading the image.

10. The method of claim 8, wherein the image is associated with one or more products.

11. The method of claim 10, wherein the label includes identifying information associated with the one or more products.

12. The method of claim 8, wherein determining the first portion of the image associated with the special mark includes:

detecting in the image a shape with black boundaries associated with a special mark pattern;

comparing content enclosed by the black boundaries to a designated content associated with the special mark pattern; and

in the event that the content enclosed by the black boundaries matches the designated content, determining that a portion of the image including the shape with the black boundaries comprises the first portion of the image associated with the special mark.

13. The method of claim 8, wherein determining the first portion of the image associated with the special mark includes:

detecting in the image a shape with black boundaries associated with a special mark pattern;

determining whether a line of pixels within the black boundaries matches a black-white pixel ratio associated with the special mark pattern; and

in the event it is determined that the line of pixels within the black boundaries matches the black-white pixel ratio associated with the special mark pattern, determining that a portion of the image including the shape with the black boundaries comprises the first portion of the image associated with the special mark.

14. The method of claim 8, further comprising, prior to applying character recognition to the second portion of the image associated with the label, extracting the second portion of the image associated with the label from the image.

15. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for:

obtaining an image;

determining a first portion of the image associated with a special mark;

determining a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark, wherein determining the second portion of the image associated with the label based at least in part on the first portion of the image associated with the special mark includes searching for the second portion of the image associated with the label in an area of the image near a location of the first portion of the image associated with the special mark; and

applying character recognition to the second portion of the image associated with the label to determine a value associated with the label.

16. The computer program product of claim 15, wherein the image is obtained based at least in part on one or more of the following:

receiving the image via a camera, receiving the image via a scanner, and downloading the image.

17. The computer program product of claim 15, wherein the image is associated with one or more products.

18. The computer program product of claim 17, wherein the label includes identifying information associated with the one or more products.

19. A system, comprising:

one or more processors configured to;

obtain an image;

determine a first portion of the image associated with a special mark, wherein to determine the first portion of the image associated with the special mark includes to;

detect in the image a shape with black boundaries associated with a special mark pattern;

compare content enclosed by the black boundaries to a designated content associated with the special mark pattern; and

in the event that the content enclosed by the black boundaries matches the designated content, determine that a portion of the image including the shape with the black boundaries comprises the first portion of the image associated with the special mark;

determine a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark; and

apply character recognition to the second portion of the image associated with the label to determine a value associated with the label; and

one or more memories coupled to the one or more processors and configured to provide the one or more processors with instructions.

20. A method, comprising:

obtaining an image;

determining, using one or more processors, a first portion of the image associated with a special mark, wherein determining the first portion of the image associated with the special mark includes;

detecting in the image a shape with black boundaries associated with a special mark pattern;

determining whether a line of pixels within the black boundaries matches a black-white pixel ratio associated with the special mark pattern; and

in the event it is determined that the line of pixels within the black boundaries matches the black-white pixel ratio associated with the special mark pattern, determining that a portion of the image including the shape with the black boundaries comprises the first portion of the image associated with the special mark;

determining a second portion of the image associated with a label based at least in part on the first portion of the image associated with the special mark; and

applying character recognition to the second portion of the image associated with the label to determine a value associated with the label.