Methods and systems for detecting screen covers on electronic devices

• US 9,885,672 B2
• Filed: 06/08/2016
• Issued: 02/06/2018
• Est. Priority Date: 06/08/2016
• 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): PATEL, KANJIBHAI B
• Application Number:
  US15/176,975
• Publication Number:
  US 20170356857A1
• Time in Patent Office: 608 Days
• Field of Search: 382141
• CPC Class Codes: G01N 21/8803 Visual inspection measuring projectors G01B9/08
• CPC Class Codes: G01N 21/958 Inspecting transparent materials or objects, e.g. windscreens for conveyed flat sheet or rod G01N21/896
• CPC Class Codes: G06Q 10/30 Administration of product recycling or disposal
• CPC Class Codes: G06Q 30/0283 Price estimation or determination
• CPC Class Codes: G06T 2207/30121 CRT, LCD or plasma display
• CPC Class Codes: G06T 7/0004 Industrial image inspection
• CPC Class Codes: G06T 7/0008 checking presence/absence
• CPC Class Codes: G06T 7/13 Edge detection
• 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 2201/06 Recognition of objects for industrial automation
• CPC Class Codes: G07F 11/72 Auxiliary equipment, e.g. for lighting cigars, opening bottles
• CPC Class Codes: G07F 9/001 Interfacing with vending machines using mobile or wearable devices
• CPC Class Codes: G07F 9/002 Vending machines being part of a centrally controlled network of vending machines
• CPC Class Codes: G07F 9/009 User recognition or proximity detection
• 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 the presence or absence of screen covers on electronic device screens are disclosed. In one embodiment, the method includes obtaining an image of a front side of an electronic device and automatically identifying line segments in the image. For each identified line segment, the method includes calculating the angle of the identified line segment. The method further includes determining an amount of the line segments having vertical or horizontal orientations. If the amount of identified vertical or horizontal line segments exceeds a predetermined threshold amount, then the presence of a screen cover is indicated.

Claims

1. A method for detecting a presence or absence of a screen cover on an electronic device, the method comprising:

receiving an image of a front side of an electronic device, the electronic device having a screen and a non-screen periphery at the front side;

automatically identifying line segments in a portion of the image corresponding to the non-screen periphery using machine vision;

determining respective angles of the identified line segments relative to a first axis of the electronic device;

determining a first amount of the identified line segments having respective angles within a first predetermined range about the first axis;

determining a second amount of the identified line segments having respective angles within a second predetermined range about a second axis orthogonal to the first axis; and

determining a presence or absence of a screen cover on the electronic device based at least in part on the first amount, the second amount, or both.

2. The method of claim 1, wherein the first predetermined range extends no more than 5 degrees off the first axis.

3. The method of claim 1, wherein the second predetermined range extends no more than 5 degrees off the second axis.

4. The method of claim 1 wherein automatically identifying the line segments using machine vision includes applying an edge detector algorithm to the image.

5. The method of claim 1 wherein:

determining the first amount includes determining a first quantity of the identified line segments having respective angles within the first predetermined range; and

determining the second amount includes determining a second quantity of the identified line segments having respective angles within the second predetermined range.

6. The method of claim 1 wherein:

determining the first amount includes determining a first extent of the identified line segments having respective angles within the first predetermined range; and

determining the second amount includes determining a second extent of the identified line segments having respective angles within the second predetermined range.

7. The method of claim 1 wherein determining the presence or absence of a screen cover on the electronic device includes determining the presence of a screen cover on the electronic device when the first amount, the second amount, or both exceeds a predetermined threshold amount.

8. The method of claim 1 wherein determining the presence or absence of a screen cover on the electronic device includes determining the absence of a screen cover on the electronic device when the first amount, the second amount, or both is less than a predetermined threshold amount.

9. The method of claim 1 wherein:

the identified line segments are first identified line segments;

the portion of the image is a first portion of the image; and

the method further comprises—

automatically identifying second line segments in a second portion of the image corresponding to the screen of the electronic device using machine vision, and

determining whether the screen is cracked based at least in part on the identified second line segments and the presence or absence of a screen cover on the electronic device.

10. The method of claim 9, further comprising determining respective positions of the identified second line segments, wherein determining whether the screen is cracked includes determining an amount of the identified second line segments, and wherein determining the amount of the identified second line segments includes giving greater weight to the identified second line segments farther from a perimeter of the second portion of the image than to the identified second line segments closer to the perimeter of the second portion of the image.

11. The method of claim 9, further comprising determining respective angles of the identified second line segments, wherein determining whether the screen is cracked includes determining an amount of the identified second line segments, and wherein determining the amount of the identified second line segments includes giving greater weight to the identified second line segments farther from having the first angle or the second angle than to the identified second line segments closer to having the first angle or the second angle.

12. A method for detecting a presence or absence of a screen cover on an electronic device, the method comprising:

receiving an image of a front side of an electronic device, the electronic device having a screen and a non-screen periphery at the front side, the non-screen periphery having four corner portions;

automatically identifying line segments in the image using machine vision;

determining respective positions of the identified line segments within the image;

determining a first amount of the identified line segments having respective positions within portions of the image corresponding to the corner portions of the non-screen periphery;

determining a second amount of the identified line segments having respective positions not within the portions of the image corresponding to the corner portions of the non-screen periphery; and

determining a presence or absence of a screen cover on the electronic device based at least in part on the first amount relative to the second amount.

13. The method of claim 12 wherein automatically identifying the line segments using machine vision includes applying an edge detector algorithm to the image.

14. The method of claim 12 wherein the corner portions extend no more than 5 cm from a horizontal edge of the electronic device and no more than 5 cm from a vertical edge of the electronic device.

15. A computer-readable memory carrying non-transitory computer-executable instructions for causing one or more processors to facilitate detecting the presence or absence of a screen cover on an electronic device, the computer-executable instructions comprising instructions that, when executed by the one or more processors:

receive an image of a front side of an electronic device, the electronic device having a screen and a non-screen periphery at the front side;

automatically identify line segments in a portion of the image corresponding to the non-screen periphery of the electronic device using machine vision;

determine respective angles of the identified line segments;

determine a first amount of the identified line segments having respective angles within a first predetermined range about a vertical angle;

determine a second amount of the identified line segments having respective angles within a second predetermined range about a horizontal angle; and

determine the presence or absence of a screen cover on the electronic device based at least in part on the first amount, the second amount, or both.

16. The computer-readable memory claim 15 wherein the computer-executable instructions, when executed by the one or more processors, automatically identify the line segments by applying an edge detector algorithm to the image.

17. The computer-readable memory of claim 15 wherein the computer-executable instructions, when executed by the one or more processors, determine the presence of a screen cover on the electronic device when the first amount, the second amount, or both exceeds a predetermined threshold amount.

18. The computer-readable memory of claim 15 wherein:

the identified line segments are first identified line segments;

the portion of the image is a first portion of the image; and

the computer-executable instructions, when executed by the one or more processors—

automatically identify second line segments in a second portion of the image corresponding to the screen of the electronic device using machine vision, and

determine whether the screen is cracked based at least in part on the identified second line segments and the presence or absence of a screen cover on the electronic device.

19. The computer-readable memory of claim 15 wherein:

the non-screen periphery has four corner portions; and

the computer-executable instructions, when executed by the one or more processors—

determine an amount of the identified line segments within portions of the image corresponding to the corner portions of the non-screen periphery, and

determine the presence or absence of a screen cover on the electronic device based at least in part on the amount of the identified line segments within the portions of the image corresponding to the corner portions of the non-screen periphery.

20. A method for detecting a presence or absence of a screen cover on an electronic device, the method comprising:

receiving an image of a front side of an electronic device;

screening segments of the image for indicia of bubbles;

identifying a number of segments of the image in which indicia of bubbles are present; and

determining a presence or absence of a screen cover on the electronic device based at least in part on the number of segments of the image in which indicia of bubbles are present.

21. The method of claim 20 wherein the segments of the image are parallel slices of the image.

22. The method of claim 20 wherein screening segments of the image for indicia of bubbles comprises, for individual segments of the image:

blurring the segment;

determining a ratio of disproportionally bright pixels to total pixels in the blurred segment; and

if the ratio exceeds a predetermined threshold, identifying indicia of bubbles in the segment.

23. The method of claim 22, wherein:

screening segments of the image for indicia of bubbles further comprises, for individual segments of the image, determining a standard deviation of brightness within the segment; and

identifying indicia of bubbles in the segment includes identifying indicia of bubbles in the segment if the standard deviation falls within a predetermined range.

24. The method of claim 23 wherein the predetermined range includes a range between about 4 and about 40 brightness units.

25. The method of claim 22 wherein the disproportionally bright pixels comprise pixels of brightness exceeding an average brightness of the blurred segment by at least a predetermined threshold amount.

26. The method of claim 25 wherein the predetermined threshold amount is at least 5%.