Recognition of numerical characters in digital images

• US 8,781,227 B2
• Filed: 08/25/2011
• Issued: 07/15/2014
• Est. Priority Date: 08/30/2010
• Status: Active Grant

• Current Assignee: Alibaba Group Holding Ltd.
• Original Assignee: Alibaba Group Holding Ltd.
• Inventors: Sun, Xiang
• Primary Examiner(s): Werner, Brian P
• Application Number:
  US13/199,332
• Publication Number:
  US 20120051645A1
• Time in Patent Office: 1,055 Days
• Field of Search: None
• US Class Current: 382/177
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/18076 by analysing connectivity, e.g. edge linking, connected component analysis or slices
• CPC Class Codes: G06V 30/32 Digital ink

Abstract

Recognition of numerical characters is disclosed, including: extracting a subimage from a received image comprising information pertaining to a plurality of numerical characters, wherein the extracted subimage is associated with one of the plurality of numerical characters; and performing recognition based at least in part on a set of topological information associated with the subimage, including: processing the subimage to obtain the set of topological information associated with the subimage; comparing the set of topological information associated with the subimage with a preset set of stored topological information; determining that in the event that the set of topological information associated with the subimage matches the preset set of stored topological information, the subimage is associated with a recognized numerical character associated with the preset set of stored topological information.

Claims

1. A system, comprising:

a processor configured to;

 

extract a subimage from a received image comprising information pertaining to a plurality of numerical characters, wherein the extracted subimage is associated with one of the plurality of numerical characters;

 

perform recognition based at least in part on a set of topological information associated with the subimage, including;

process the subimage to obtain the set of topological information associated with the subimage, wherein the processing of the subimage includes;

 

obtain the set of topological information by extracting one or more vertices and one or more edges associated with the subimage; and

 

determine whether a closed ring associated with at least a portion of the one or more vertices and at least a portion of the one or more edges exists, wherein the determining whether the closed ring exists comprises;

proceed from a first filled in pixel to a second filled in pixel, the second filled in pixel being adjacent to the first filled in pixel;

proceed from the second filled in pixel to a third filled in pixel repeatedly until the first filled in pixel is reached, the third filled in pixel being adjacent to the second filled in pixel; and

in the event that the first filled in pixel is reached;

 

associate a point within the closed ring as representing the closed ring; and

 

add a location of the point representing the closed ring to the set of topological information;

compare the set of topological information associated with the subimage with a preset set of stored topological information;

determine that in the event that the set of topological information associated with the subimage matches the preset set of stored topological information, the subimage is associated with a recognized numerical character associated with the preset set of stored topological information; and

a memory coupled to the processor and configured to provide the processor with instructions.

2. The system of claim 1, wherein the processor is further configured to refine the subimage.

3. The system of claim 2, wherein to refine the subimage includes to apply image degradation to the subimage.

4. The system of claim 1, wherein the preset set of stored topological information is stored in a database.

5. The system of claim 1, wherein the processor is further configured to display the recognized numerical character.

6. The system of claim 1, wherein the recognized numerical character is one of the following:

0, 1, 2, 3, 4, 5, 6, 7, 8, or 9.

14. The system of claim 1, wherein the point within the determined closed ring is a central point of the closed ring.

7. A method, comprising:

extracting a subimage from a received image comprising information pertaining to a plurality of numerical characters, wherein the extracted subimage is associated with one of the plurality of numerical characters; and

performing recognition based at least in part on a set of topological information associated with the subimage, including;

processing the subimage to obtain the set of topological information associated with the subimage, wherein the processing of the subimage includes;

obtaining the set of topological information by extracting one or more vertices and one or more edges associated with the subimage; and

determining whether a closed ring associated with at least a portion of the one or more vertices and at least a portion of the one or more edges exists, wherein the determining whether the closed ring exists comprises;

proceeding from a first filled in pixel to a second filled in pixel, the second filled in pixel being adjacent to the first filled in pixel;

proceeding from the second filled in pixel to a third filled in pixel repeatedly until the first filled in pixel is reached, the third filled in pixel being adjacent to the second filled in pixel; and

in the event that the first filled in pixel is reached;

 

associating a point within the closed ring as representing the closed ring; and

 

adding a location of the point representing the closed ring to the set of topological information;

comparing the set of topological information associated with the subimage with a preset set of stored topological information;

determining that in the event that the set of topological information associated with the subimage matches the preset set of stored topological information, the subimage is associated with a recognized numerical character associated with the preset set of stored topological information.

8. The method of claim 7, further comprising refining the subimage.

9. The method of claim 8, wherein refining the subimage includes applying image degradation to the subimage.

10. The method of claim 7, wherein the preset set of stored topological information is stored in a database.

11. The method of claim 7, further comprising displaying the recognized numerical character.

12. The method of claim 7, wherein the recognized numerical character is one of the following:

0, 1, 2, 3, 4, 5, 6, 7, 8, or 9.

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

extracting a subimage from a received image comprising information pertaining to a plurality of numerical characters, wherein the extracted subimage is associated with one of the plurality of numerical characters; and

performing recognition based at least in part on a set of topological information associated with the subimage, including;

processing the subimage to obtain the set of topological information associated with the subimage, wherein the processing of the subimage includes;

obtaining the set of topological information by extracting one or more vertices and one or more edges associated with the subimage; and

determining whether a closed ring associated with at least a portion of the one or more vertices and at least a portion of the one or more edges exists, wherein the determining whether the closed ring exists comprises;

proceeding from a first filled in pixel to a second filled in pixel, the second filled in pixel being adjacent to the first filled in pixel;

proceeding from the second filled in pixel to a third filled in pixel repeatedly until the first filled in pixel is reached, the third filled in pixel being adjacent to the second filled in pixel; and

in the event that the first filled in pixel is reached;

 

associating a point within the closed ring as representing the closed ring; and

 

adding a location of the point representing the closed ring to the set of topological information;

comparing the set of topological information associated with the subimage with a preset set of stored topological information;

determining that in the event that the set of topological information associated with the subimage matches the preset set of stored topological information, the subimage is associated with a recognized numerical character associated with the preset set of stored topological information.