Aspect ratio validation

• US 9,594,947 B1
• Filed: 09/30/2014
• Issued: 03/14/2017
• Est. Priority Date: 09/30/2014
• Status: Active Grant

• Current Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Original Assignee: Amazon Technologies, Inc. (Amazon.com, Inc.)
• Inventors: Kotagiri, Srikanth, Waggoner, Charles Benjamin Franklin
• Primary Examiner(s): Ahmed, Samir
• Application Number:
  US14/503,213
• Time in Patent Office: 896 Days
• Field of Search: 348/441, 348/445, 348/459, 348/403.1, 348/556, 348/558, 348/403
• US Class Current: 1/1
• CPC Class Codes: G06V 20/41 Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items segmenting video sequences G06V20/49
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/164 using holistic features
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

A technology for aspect ratio validation is provided. An object may be detected in a visual media presentation. The detected object may be compared to a first candidate aspect ratio object of a same class of objects as the object. The detected object may also be compared to a second candidate aspect ratio object, which may also be of a same class of objects as the detected object. A determination may be made as to which of the first and second candidate aspect ratio objects the object corresponds.

Claims

1. A computer-implemented method, comprising:

detecting an object in a visual media presentation;

comparing the object to a first candidate aspect ratio object of a same class of objects as the object;

comparing the object to a second candidate aspect ratio object of the same class of objects as the object;

determining a difference in aspect ratio of the object as compared to the first or second candidate aspect ratio objects by comparing proportions of the object with proportions of the first or second candidate aspect ratio objects; and

determining to which of the first and second candidate aspect ratio objects the object corresponds.

2. The method of claim 1, further comprising modifying an aspect ratio of the first candidate aspect ratio object to create the second candidate aspect ratio object.

3. The method of claim 1, further comprising modifying the visual media presentation based on the difference in aspect ratio.

4. The method of claim 1, further comprising flagging the visual media presentation as having an incorrect aspect ratio when one of the first or second candidate aspect ratio objects has an incorrect aspect ratio and an aspect ratio of the object is similar to an aspect ratio object of the one of the first or second candidate aspect ratio objects.

5. The method of claim 4, further comprising sending a notification to a provider of the visual media presentation of the flagged visual media presentation representing that the visual media presentation has the incorrect aspect ratio.

6. The method of claim 1, further comprising determining that the object has an incorrect aspect ratio when a difference between an aspect ratio of the object and an aspect ratio of one of the first or second candidate aspect ratio objects is greater than a predetermined percentage difference.

7. The method of claim 1, further comprising identifying a face of a known person in the visual media presentation as the object and comparing the face to a properly proportioned face image of the known person.

8. The method of claim 1, further comprising using machine learning to learn to identify an aspect ratio of the visual media presentation based on the comparison of the object to the first or second candidate aspect ratio objects.

9. The method of claim 1, wherein comparing the object to the first or second candidate aspect ratio objects further comprises scaling the first or second candidate aspect ratio objects to a same size as the object and identifying specific dimensions or ranges of dimensions of features of the object in the visual media presentation.

10. The method of claim 1, further comprising identifying ratios of features of the object in the visual media presentation.

11. The method of claim 1, further comprising determining whether an aspect ratio of the visual media presentation is correct and regenerating the visual media presentation with a correct aspect ratio when the aspect ratio of the visual media presentation is incorrect.

13. The method of claim 1, further comprising modifying an aspect ratio of the first candidate aspect ratio object to create the second candidate aspect ratio object.

14. The method of claim 1, further comprising determining a difference in aspect ratio of the object as compared to the first or second candidate aspect ratio objects by comparing proportions of the object with proportions of the first or second candidate aspect ratio objects.

15. The method of claim 1, further comprising sending a notification to a provider of the visual media presentation of the flagged visual media presentation representing that the visual media presentation has the incorrect aspect ratio.

16. The method of claim 1, further comprising determining that the object has an incorrect aspect ratio when a difference between an aspect ratio of the object and an aspect ratio of one of the first or second candidate aspect ratio objects is greater than a predetermined percentage difference.

12. A computer-implemented method, comprising:

detecting an object in a visual media presentation;

comparing the object to a first candidate aspect ratio object of a same class of objects as the object;

comparing the object to a second candidate aspect ratio object of the same class of objects as the object;

determining to which of the first and second candidate aspect ratio objects the object corresponds; and

flagging the visual media presentation as having an incorrect aspect ratio when one of the first or second candidate aspect ratio objects has an incorrect aspect ratio and an aspect ratio of the object is similar to an aspect ratio object of the one of the first or second candidate aspect ratio objects.

17. A non-transitory machine readable storage medium having instructions embodied thereon, the instructions when executed cause a processor to perform a method, the method comprising:

detecting an object in a visual media presentation;

comparing the object to a first candidate aspect ratio object of a same class of objects as the object;

comparing the object to a second candidate aspect ratio object of the same class of objects as the object;

determining to which of the first and second candidate aspect ratio objects the object corresponds; and

flagging the visual media presentation as having an incorrect aspect ratio when one of the first or second candidate aspect ratio objects has an incorrect aspect ratio and an aspect ratio of the object is similar to an aspect ratio object of the one of the first or second candidate aspect ratio objects.

18. The non-transitory machine readable storage medium of claim 17, further comprising determining a difference in aspect ratio of the object as compared to the first or second candidate aspect ratio objects by comparing proportions of the object with proportions of the first or second candidate aspect ratio objects.

19. The non-transitory machine readable storage medium of claim 17, further comprising determining whether an aspect ratio of the visual media presentation is correct and regenerating the visual media presentation with a correct aspect ratio when the aspect ratio of the visual media presentation is incorrect.