Methods and systems for detecting cracks in electronic devices

• US 10,127,647 B2
• Filed: 04/15/2016
• Issued: 11/13/2018
• Est. Priority Date: 04/15/2016
• Status: Active Grant

• Current Assignee: Ecoatm Incorporated (Coinstar Asset Holdings, LLC)
• Original Assignee: Ecoatm Incorporated (Coinstar Asset Holdings, LLC)
• Inventors: Forutanpour, Babak, Ploetner, Jeffrey
• Primary Examiner(s): Motsinger, Sean
• Application Number:
  US15/130,851
• Publication Number:
  US 20170301078A1
• Time in Patent Office: 942 Days
• CPC Class Codes: G01N 21/88 Investigating the presence of flaws or contamination
• CPC Class Codes: G06T 2207/20061 Hough transform
• CPC Class Codes: G06T 2207/30108 Industrial image inspection
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• CPC Class Codes: Y02W 90/00 Enabling technologies or technologies with a potential or indirect contribution to greenhouse gas [GHG] emissions mitigation

Abstract

Systems and methods for detecting cracks in an electronic device are disclosed. In one embodiment, the method includes receiving an image of a front side of a mobile device and automatically identifying edges in the image. For given edges among the identified edges, the method includes determining whether another edge among the identified edges is present within a predetermined distance of the given edge. Next, straight line segments corresponding to the edges for which another edge is within the predetermined distance are identified, and then a crack evaluation assessment is assigned to the mobile device based at least in part on the identified straight line segments.

Claims

1. A method performed by one or more computing devices for detecting cracks in an electronic device, the method comprising:

receiving an image of an electronic device;

automatically identifying a plurality of edges in the image;

for individual edges among the identified edges, determining whether another edge among the identified edges is present within a predetermined distance of each of the individual edges;

automatically identifying straight line segments corresponding to the individual edges for which another edge is within the predetermined distance; and

evaluating a condition of the electronic device based at least in part on the number of identified straight line segments.

2. The method of claim 1 wherein:

automatically identifying the straight line segments includes applying a Hough line transform to the edges for which another edge is within the predetermined distance, and

evaluating a condition of the electronic device includes assigning the crack evaluation assessment based at least in part on a result of applying the Hough line transform.

3. The method of claim 1 wherein determining, respectively, whether another edge among the identified edges is present within the predetermined distance comprises:

for a given point along an individual edge among the identified edges;

determining whether another edge among the identified edges is present within a first predetermined distance along a first axis; and

determining whether another edge among the identified edges is present within a second predetermined distance along a second axis orthogonal to the first axis.

4. The method of claim 1 wherein automatically identifying the edges comprises applying a Canny edge detector to the image.

5. The method of claim 1 wherein the image is of a screen and a non-screen portion of the electronic device, and wherein the method further comprises applying a first filter to the screen portion and applying a second filter to the non-screen portion before automatically identifying the edges.

6. The method of claim 1 wherein the predetermined distance is not more than about 1.5 mm.

7. The method of claim 1 wherein evaluating a condition of the electronic device comprises calculating a number of pixels in the image that are included in the identified straight line segments.

8. The method of claim 1, further comprising determining a value for the electronic device based on the evaluated condition of the electronic device.

9. A method performed by one or more computing devices for detecting cracks in an electronic device, the method comprising:

receiving an image of an electronic device;

automatically identifying a plurality of edges in the image;

automatically determining whether individual edges among the identified edges are within a pre-selected proximity to other individual edges among the identified edges; and

assessing the condition of the electronic device based at least in part on the number of the edges within the pre-selected proximity to other edges.

10. The method of claim 9 wherein, in assessing the condition of the electronic device, the edges not within the pre-selected proximity to other edges have no weight.

11. The method of claim 9 wherein automatically determining whether individual edges among the identified edges are within a pre-selected proximity to other individual edges among the identified edges comprises:

for an individual edge among the identified edges;

determining whether another edge among the identified edges is present within a first predetermined distance along a first axis;

determining whether another edge among the identified edges is present within a second predetermined distance along a second axis orthogonal to the first axis; and

if another edge among the identified edges is present within the first predetermined distance along the first axis or within the second predetermined distance along the second axis, then indicating that the individual edge is within the pre-selected proximity to the other edge.

12. The method of claim 11 wherein the first predetermined distance is not more than about 1.5 mm.

13. The method of claim 9 wherein assessing the electronic device comprises calculating a number of pixels in the image that are included in the individual edges that are within the pre-selected proximity to other individual edges.

14. A method performed by one or more computing devices for detecting cracks in an electronic device, the method comprising:

receiving an image of an electronic device;

automatically identifying one or more edges in the image;

identifying edge-to-non-edge-to-edge groupings among the identified edges; and

assessing the condition of the electronic device based at least in part on the identified edge-to-non-edge-to-edge groupings, wherein, in the assessment, the edges in the identified edge-to-non-edge-to-edge groupings have greater weight than other edges among the identified edges.

15. The method of claim 14 wherein identifying edge-to-non-edge-to-edge groupings comprises:

for an individual edge among the identified edges;

determining whether another edge among the identified edges is present within a first predetermined distance along a first axis; and

determining whether another edge among the identified edges is present within a second predetermined distance along a second axis orthogonal to the first axis.

16. The method of claim 14, wherein assessing the condition of the electronic device comprises calculating a number of pixels in the image that are included in the identified edge-to-non-edge-to-edge groupings.

17. A computer-readable memory carrying computer-executable instructions for causing one or more processors to facilitate detecting cracks in an electronic device, the computer-executable instructions comprising instructions that, when executed by the one or more processors:

receive an image of an electronic device;

automatically identify edges in the image;

for individual edges among the identified edges, determine whether another edge among the identified edges is present within a predetermined distance of the individual edge;

automatically identify straight line segments corresponding to the edges for which another edge is within the predetermined distance; and

evaluate a condition of the electronic device based at least in part on the identified straight line segments.

18. The computer-readable memory of claim 17 wherein the computer-executable instructions, when executed by the one or more processors:

automatically identify the straight line segments at least in part by applying a Hough line transform to the edges for which another edge is within the predetermined distance; and

evaluate the condition of the electronic device at least in part by assigning a crack evaluation assessment based at least in part on a result of applying the Hough line transform.

19. The computer-readable memory of claim 17 wherein the computer-executable instructions, when executed by the one or more processors, determine, respectively, whether another edge among the identified edges is present within the predetermined distance of an individual edge among the identified edges at least in part by:

for a given point along the individual edge;

determining whether another edge among the identified edges is present within a first predetermined distance along a first axis; and

determining whether another edge among the identified edges is present within a second predetermined distance along a second axis orthogonal to the first axis.

20. The computer-readable memory of claim 17 wherein the computer-executable instructions, when executed by the one or more processors, automatically identify the straight line segments at least in part by applying a Canny edge detector to the image.

21. The computer-readable memory of claim 17 wherein the computer-executable instructions, when executed by the one or more processors, assign the crack evaluation assessment based at least in part on a number of pixels in the image that are included in the identified straight line segments.