Producing a flowchart object from an image

Patent metadata

Field	Value
Publication number	US-9934431-B2
Application number	US-201615221315-A
Country	US
Kind code	B2
Filing date	Jul 27, 2016
Priority date	Jul 27, 2016
Publication date	Apr 3, 2018
Grant date	Apr 3, 2018

Abstract

A method for image processing. The method includes: reading an image of a flowchart; identifying, within the image, a plurality of paths corresponding to the flowchart; classifying a first path of the plurality of paths as a flowchart element by: calculating, during a solo evaluation phase, a plurality of established likelihood scores for the first path based on a plurality of properties of the first path; calculating, during a neighbor-based evaluation phase, a first plurality of provisional likelihood scores for the first path based on the plurality of established likelihood scores for the first path and a plurality of established likelihood scores for a second path of the plurality of paths; and updating, during the neighbor-based evaluation phase, the plurality of established likelihood scores for the first path based on the first plurality of provisional likelihood scores; and generating a flowchart object based on the classified first path.

First claim

What is claimed is:

1. A method for image processing, comprising:
reading an image of a flowchart;
identifying, within the image, a plurality of paths corresponding to the flowchart;
classifying a first path of the plurality of paths as a flowchart element by:
calculating, during a solo evaluation phase, a plurality of established likelihood scores for the first path based on a plurality of properties of the first path;
calculating, during a neighbor-based evaluation phase, a first plurality of provisional likelihood scores for the first path based on the plurality of established likelihood scores for the first path and a plurality of established likelihood scores for a second path of the plurality of paths; and
updating, during the neighbor-based evaluation phase, the plurality of established likelihood scores for the first path based on the first plurality of provisional likelihood scores; and

generating a flowchart object based on the classified first path.

2. The method of claim 1 , further comprising:
grouping a subset of the paths into a group,
wherein calculating the first plurality of provisional likelihood scores is further based on a likelihood score for the group.

3. The method of claim 1 , wherein updating the plurality of established likelihood scores comprises multiplying the first plurality of provisional likelihood scores by an update strength.

4. The method of claim 1 , wherein classifying the first path further comprises:
calculating, during the solo evaluation phase, a second plurality of provisional likelihood scores for the first path based on the plurality of properties of the first path.

5. The method of claim 1 , wherein classifying the first path further comprises:
updating the plurality of established likelihood scores for the second path;
calculating, during the neighbor-based evaluation phase, a second plurality of provisional likelihood scores for the first path based on the plurality of updated established likelihood scores for the first path and the plurality of updated established likelihood scores for the second path; and
updating, during the neighbor-based evaluation phase, the plurality of updated established likelihood scores for the first path based on the second plurality of provisional likelihood scores.

6. The method of claim 1 , wherein the first path intersects a second path at an endpoint of the second path.

7. The method of claim 2 , wherein the plurality of paths and the group are each classified as one selected from a group consisting of: a node, a connector body, a connector cap, a complete connector, a node content, and a connector label.

8. The method of claim 1 , wherein the properties comprise information representing: a degree of an enclosed region formed by a path; a degree of enclosure that the path encloses another path; degrees of similarity between the path and a rectangle, a circle, a diamond, text, and an arrow; and a relative size to another path.

9. The method of claim 1 , wherein each of the plurality of established likelihood scores for the first path corresponds to a different flowchart element and has a confidence value between 0 and 1, and wherein the first plurality of provisional likelihood scores are calculated with at least one fuzzy logic system.

10. The method of claim 2 , further comprising executing character recognition on an interior of the group in response to the group being classified as a node.

11. A non-transitory computer readable medium (CRM) storing computer readable program code that is executable by a processor such that the processor:
reads an image of a flowchart;
identifies, within the image, a plurality of paths corresponding to the flowchart;
classifies a first path of the plurality of paths as a flowchart element by:
calculating, during a solo evaluation phase, a plurality of established likelihood scores for the first path based on a plurality of properties of the first path;
calculating, during a neighbor-based evaluation phase, a first plurality of provisional likelihood scores for the first path based on the plurality of established likelihood scores for the first path and a plurality of established likelihood scores for a second path of the plurality of paths; and
updating, during the neighbor-based evaluation phase, the plurality of established likelihood scores for the first path based on the first plurality of provisional likelihood scores; and

generates a flowchart object based on the classified first path.

12. The non-transitory CRM of claim 11 , wherein the computer readable program code further:
groups a subset of the paths into a group,
wherein calculating the first plurality of provisional likelihood scores is further based on a likelihood score for the group.

13. The non-transitory CRM of claim 11 , wherein updating the plurality of established likelihood scores comprises multiplying the first plurality of provisional likelihood scores by an update strength.

14. The non-transitory CRM of claim 11 , wherein classifying the first path further comprises:
calculating, during the solo evaluation phase, a second plurality of provisional likelihood scores for the first path based on the plurality of properties of the first path.

15. The non-transitory CRM of claim 11 , wherein classifying the first path further comprises:
updating the plurality of established likelihood scores for the second path;
calculating, during the neighbor-based evaluation phase, a second plurality of provisional likelihood scores for the first path based on the plurality of updated established likelihood scores for the first path and the plurality of updated established likelihood scores for the second path; and
updating, during the neighbor-based evaluation phase, the plurality of updated established likelihood scores for the first path based on the second plurality of provisional likelihood scores.

16. The non-transitory CRM of claim 11 , wherein the properties comprise information representing: a degree of an enclosed region formed by a path; a degree of enclosure that the path encloses another path; degrees of similarity between the path and a rectangle, a circle, a diamond, text, and an arrow; and a relative size to another path.

17. An image processing system comprising:
a memory; and
a processor connected to the memory that:
reads an image of a flowchart;
identifies, within the image, a plurality of paths corresponding to the flowchart;
classifies a first path of the plurality of paths as a flowchart element by:
calculating, during a solo evaluation phase, a plurality of established likelihood scores for the first path based on a plurality of properties of the first path;
calculating, during a neighbor-based evaluation phase, a first plurality of provisional likelihood scores for the first path based on the plurality of established likelihood scores for the first path and a plurality of established likelihood scores for a second path of the plurality of paths; and
updating, during the neighbor-based evaluation phase, the plurality of established likelihood scores for the first path based on the first plurality of provisional likelihood scores; and

generates a flowchart object based on the classified first path.

18. The image processing system of claim 17 , wherein the processor also groups a subset of the paths into a group, and wherein calculating the first plurality of provisional likelihood scores is further based on a likelihood score for the group.

19. The image processing system of claim 17 , wherei

Assignees

• Konica Minolta Laboratory Usa Inc

Inventors

• Prebble Tim

Classifications

• G06V30/10

  Character recognition · CPC title

• G06K2209/01

  Physics · mapped topic

• G06K9/00449

  Physics · mapped topic

• G06K9/00476

  Physics · mapped topic

• G06K9/00456 Primary

  Physics · mapped topic