Shape detection

• US 10,176,403 B2
• Filed: 05/24/2017
• Issued: 01/08/2019
• Est. Priority Date: 05/24/2016
• Status: Active Grant

• Current Assignee: Idemia Identity & Security USA, LLC (Advent International Corporation)
• Original Assignee: Morphotrust USA Incorporated (Advent International Corporation)
• Inventors: Martin, Brian K.
• Primary Examiner(s): Kassa, Yosef
• Application Number:
  US15/604,424
• Publication Number:
  US 20170344857A1
• Time in Patent Office: 594 Days
• Field of Search: 382154, 382199, 382266, 382269, 382282, 382286, 382294, 382295, 382298, 358 12, 358 315, 358 327
• CPC Class Codes: G06F 18/24 Classification techniques
• CPC Class Codes: G06V 10/247 by affine transforms, e.g. correction due to perspective effects; Quadrilaterals, e.g. trapezoids
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 30/414 Extracting the geometrical structure, e.g. layout tree; Block segmentation, e.g. bounding boxes for graphics or text

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for shape detection are disclosed. In one aspect, a method includes the actions of generating a shape model that includes a predetermined shape with a predetermined scale and predetermined orientation. The actions further include receiving an image. The actions further include identifying edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model. The actions further include selecting a plurality of edges that likely correspond to edges of a shape that is similar to the shape model. The actions further include determining a fit score between the plurality of edges and each shape of a plurality of shapes that are similar to the shape model. The actions further include identifying a particular shape in the image that most closely fits the shape model.

Claims

1. A computer-implemented method comprising:

generating a shape model that includes a predetermined shape with a predetermined scale and predetermined orientation;

receiving an image;

identifying, in the image for each side of the shape model, edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model;

selecting, from among the identified edges, a plurality of edges that have a highest contrast;

determining a fit score between the plurality of edges and each shape of a plurality of shapes that are similar to the shape model; and

based on each fit score, identifying, from among the plurality of shapes, a particular shape that most closely fits the shape model.

2. The method of claim 1, wherein the shape model and the particular shape have a same number of edges.

3. The method of claim 1, wherein the predetermined distance from the side of the shape model is a predetermined number of pixels.

4. The method of claim 1, wherein identifying a particular shape in the image that most closely fits the shape model comprises identifying the particular shape with a highest fit score.

5. The method of claim 1, wherein identifying, in the image for each side of the shape model, edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model comprises identifying the edges at predetermined pixel intervals.

6. The method of claim 1, wherein the shape model has straight edges.

7. The method of claim 1, wherein selecting, from among the identified edges, a plurality of edges that have a highest contrast comprises selecting the plurality of edges have a largest gradient among the identified edges.

8. A system comprising:

one or more computers; and

one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

generating a shape model that includes a predetermined shape with a predetermined scale and predetermined orientation;

receiving an image;

identifying, in the image for each side of the shape model, edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model;

selecting, from among the identified edges, a plurality of edges that have a highest contrast;

determining a fit score between the plurality of edges and each shape of a plurality of shapes that are similar to the shape model; and

based on each fit score, identifying, from among the plurality of shapes, a particular shape that most closely fits the shape model.

9. The system of claim 8, wherein the shape model and the particular shape have a same number of edges.

10. The system of claim 8, wherein the predetermined distance from the side of the shape model is a predetermined number of pixels.

11. The system of claim 8, wherein identifying a particular shape in the image that most closely fits the shape model comprises identifying the particular shape with a highest fit score.

12. The system of claim 8, wherein identifying, in the image for each side of the shape model, edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model comprises identifying the edges at predetermined pixel intervals.

13. The system of claim 8, wherein the shape model has straight edges.

14. The system of claim 8, wherein selecting, from among the identified edges, a plurality of edges that have a highest contrast comprises selecting the plurality of edges have a largest gradient among the identified edges.

16. The system of claim 8, wherein the shape model and the particular shape have a same number of edges.

17. The system of claim 8, wherein the predetermined distance from the side of the shape model is a predetermined number of pixels.

18. The system of claim 8, wherein identifying a particular shape in the image that most closely fits the shape model comprises identifying the particular shape with a highest fit score.

19. The system of claim 8, wherein identifying, in the image for each side of the shape model, edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model comprises identifying the edges at predetermined pixel intervals.

20. The system of claim 8, wherein the shape model has straight edges.

15. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

generating a shape model that includes a predetermined shape with a predetermined scale and predetermined orientation;

receiving an image;

identifying, in the image for each side of the shape model, edges that are parallel to the side of the shape model and that are a predetermined distance from the side of the shape model;

selecting, from among the identified edges, a plurality of edges that have a highest contrast;

determining a fit score between the plurality of edges and each shape of a plurality of shapes that are similar to the shape model; and

based on each fit score, identifying, from among the plurality of shapes, a particular shape that most closely fits the shape model.