Detecting an image obstruction

• US 10,547,801 B2
• Filed: 10/26/2017
• Issued: 01/28/2020
• Est. Priority Date: 10/26/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Cheaz, Nixon, Diaz, Anthony, Shetty, Rohit, Gebhardt, Richard A.
• Primary Examiner(s): Tissire, Abdelaaziz
• Application Number:
  US15/794,103
• Publication Number:
  US 20190132530A1
• Time in Patent Office: 824 Days
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/70 Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: H04N 25/60 Noise processing, e.g. detecting, correcting, reducing or removing noise

Abstract

Detection of an image obstruction is facilitated by, in part, obtaining multiple frames of an image being captured via an imaging device, and confirming movement of the imaging device between the multiple frames. The movement causes perspective shifting of the image between frames and the perspective shifting results in one or more objects of the image shifting between frames. The detection process determines whether an edge object within the multiple frames does not shift in a manner corresponding to the one or more objects between the multiple frames, and based, at least in part, on determining that the edge object does not shift in the corresponding manner to the one or more objects, identifying the edge object as an image obstruction. Presence of the identified image obstruction is signaled to facilitate corrective action being taken.

Claims

1. A method comprising:

obtaining multiple frames of an image being captured via an imaging device;

confirming movement of the imaging device between the multiple frames, the movement causing perspective shifting of the image between the multiple frames, the perspective shifting causing one or more objects of the image to shift between frames;

determining, by a processor, whether an edge object within the multiple frames does not shift in a corresponding manner to the one or more objects between the multiple frames;

based, at least in part, on determining that the edge object does not shift in the corresponding manner to the one or more objects between the multiple frames, assigning one or more points to a confidence score for the edge object, the confidence score being an accumulation of points based on the assigning;

comparing the confidence score to a set threshold, the set threshold being pre-defined and indicating that the edge object is an image obstruction;

based on the confidence score not exceeding the set threshold, repeating the obtaining, confirming, determining, assigning, and comparing until the confidence score exceeds the set threshold or the confidence score is reset;

based on the confidence score exceeding the set threshold, identifying the edge object as the image obstruction; and

based on the identifying, signaling presence of the identified image obstruction to facilitate corrective action.

2. The method of claim 1, further comprising, prior to the determining, identifying presence of the edge object within the multiple frames, the edge object being an object at an edge of the multiple frames.

3. The method of claim 2, further comprising resetting the confidence score based on the edge object shifting correspondingly to the one or more objects between the multiple frames.

4. The method of claim 1, wherein the determining comprises determining that the edge object within the multiple frames remains at a substantially fixed location between the multiple frames notwithstanding the perspective shifting of the imaging device between the multiple frames.

5. The method of claim 1, wherein the determining further comprises determining that the edge object within the multiple frames shifts in a direction that does not correlate with the shifting of the one or more objects between the multiple frames.

6. The method of claim 1, wherein the confirming comprises comparing content of the multiple frames to confirm that the perspective of the image has shifted between the multiple frames.

7. The method of claim 1, wherein the signaling comprises at least one of vibrating the imaging device or providing an imaging device audio signal to notify a user of the imaging device of the presence of the identified image obstruction.

8. The method of claim 1, further comprising providing a cropping option to facilitate removal of the identified image obstruction from the image.

9. The method of claim 1, further comprising prior to the determining, resetting the confidence score based on the edge object not being identified within the multiple frames.

10. A system for facilitating detecting of an image obstruction, the system comprising:

a memory; and

a processing circuit communicatively coupled to the memory, wherein the system performs a method comprising;

obtaining multiple frames of an image being captured via an imaging device;

confirming movement of the imaging device between the multiple frames, the movement causing perspective shifting of the image between the multiple frames, the perspective shifting causing one or more objects of the image to shift between frames;

determining whether an edge object within the multiple frames does not shift in a corresponding manner to the one or more objects between multiple frames;

based, at least in part, on determining that the edge object does not shift in the corresponding manner to the one or more objects between the multiple frames, assigning one or more points to a confidence score for the edge object, the confidence score being an accumulation of points based on the assigning;

comparing the confidence score to a set threshold, the set threshold being pre-defined and indicating that the edge object is an image obstruction;

based on the confidence score not exceeding the set threshold, repeating the obtaining, confirming, determining, assigning, and comparing until the confidence score exceeds the set threshold or the confidence score is reset;

based on the confidence score exceeding the set threshold, identifying the edge object as the image obstruction; and

based on the identifying, signaling presence of the identified image obstruction to facilitate corrective action.

11. The system of claim 10, further comprising, prior to the determining, identifying presence of the edge object within the multiple frames, the edge object being an object at an edge of the multiple frames.

12. The method of claim 11, further comprising resetting the confidence score based on the edge object shifting correspondingly to the one or more objects between the multiple frames.

13. The system of claim 10, wherein the determining comprises determining that the edge object within the multiple frames remains at a substantially fixed location between the multiple frames notwithstanding the perspective shifting of the imaging device between the multiple frames.

14. The system of claim 10, wherein the determining further comprises determining that the edge object within the multiple frames shifts in a direction that does not correlate with the shifting of the one or more objects between the multiple frames.

15. The system of claim 10, wherein the confirming comprises comparing content of the multiple frames to confirm that the perspective of the image has shifted between the multiple frames.

16. The method of claim 10, further comprising prior to the determining, resetting the confidence score based on the edge object not being identified within the multiple frames.

17. A computer program product for facilitating detecting an image obstruction, the computer program product comprising:

a computer readable storage medium having computer readable program code embodied therewith, the computer readable program code being executable by a processor to perform a method comprising;

obtaining multiple frames of an image being captured via an imaging device;

confirming movement of the imaging device between the multiple frames, the movement causing perspective shifting of the image between the multiple frames, the perspective shifting causing one or more objects of the image to shift between frames;

determining whether an edge object within the multiple frames does not shift in a corresponding manner to the one or more objects between multiple frames;

based, at least in part, on determining that the edge object does not shift in the corresponding manner to the one or more objects between the multiple frames, assigning one or more points to a confidence score for the edge object, the confidence score being an accumulation of points based on the assigning;

comparing the confidence score to a set threshold, the set threshold being pre-defined and indicating that the edge object is an image obstruction;

based on the confidence score not exceeding the set threshold, repeating the obtaining, confirming, determining, assigning, and comparing until the confidence score exceeds the set threshold or the confidence score is reset based on the confidence score exceeding the set threshold, identifying the edge object as the image obstruction; and

based on the identifying, signaling presence of the identified image obstruction to facilitate corrective action.

18. The computer program product of claim 17, further comprising, prior to the determining, identifying presence of the edge object within the multiple frames, the edge object being an object at an edge of the multiple frames.

19. The computer program product of claim 17, wherein the determining comprises determining that the edge object within the multiple frames remains substantially fixed location between the multiple frames notwithstanding the perspective shifting of the imaging device between the multiple frames.

20. The computer program product of claim 17, wherein the determining further comprises determining that the edge object within the multiple frames shifts in a direction that does not correlate with the shifting of the one or more objects between the multiple frames.