Creation of representative content based on facial analysis

• US 10,311,284 B2
• Filed: 04/26/2017
• Issued: 06/04/2019
• Est. Priority Date: 04/28/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Lee, David, Chan, Chunkit Jacky, Ricard, Doug, Scott, Stacia, Light, Allison
• Primary Examiner(s): Kassa, Yosef
• Application Number:
  US15/497,423
• Publication Number:
  US 20170228583A1
• Time in Patent Office: 769 Days
• Field of Search: 382115, 382117, 382118, 382209, 382278, 340 581, 340 582, 340 583
• CPC Class Codes: C07C 1/00 Preparation of hydrocarbons from one or more compounds, none of them being a hydrocarbon
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/168 Feature extraction; Face representation
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G06V 40/193 Preprocessing; Feature extraction

Abstract

Technologies for analyzing various features detected in a face detected in an image. Such features may include at least the eyes, eyebrows, node, and mouth of a face. Such analyzing may include scoring aspects of these features. Such scores may be weighted. The analysis may be used to determine expressions and/or poses of the face, as well as indicate if the face is smiling, frowning, or neutral. An overall quality score for the face may also be determined and provided based on the aforementioned analysis as well as whether or not the face is near an edge of the image or cut-off in the image. Finally, a face signature may be determined that uniquely identifies the face, at least within the scope of the analyzed features. Such face signatures may be used to detect a similar face in other images.

Claims

1. A method performed on a computing device, the method comprising:

assigning a face identifier to a first face detected in a first image, the first face belonging to a person;

generating, by the computing device, a set of facial feature descriptors based on an analysis of the first face detected in the first image and on the face identifier of the first face, each of the facial feature descriptors corresponding to an analyzed physical feature of the first face detected in the first image; and

generating, by the computing device and based on the set of facial feature descriptors, a face signature that uniquely identifies a second face detected in a second image as belonging to the same person.

2. The method of claim 1 further comprising:

generating, by the computing device and based on the set of facial feature descriptors, a quality score of the first face.

3. The method of claim 2 where the quality score is determined based partially on the location of the first face within the first image.

4. The method of claim 2 where the quality score is based partially on the amount of the first face in the first image.

5. The method of claim 1 further comprising:

generating, by the computing device and based on the set of facial feature descriptors, an expression of the first face.

6. The method of claim 1 further comprising:

generating, by the computing device and based on the set of facial feature descriptors, a pose of the first face.

7. A computing device comprising:

a processor;

memory coupled to the processor;

a program module that is stored in the memory and that, based on execution by the processor, configures the computing device to perform actions comprising;

assigning a face identifier to a first face detected in a first image, the first face belonging to a person;

generating, by the computing device, a set of facial feature descriptors based on an analysis of the first face detected in the first image and on the face identifier of the first face, each of the facial feature descriptors corresponding to an analyzed physical feature of the first face detected in the first image; and

generating, by the computing device and based on the set of facial feature descriptors, a face signature that uniquely identifies a second face detected in a second image as belonging to the same person.

8. The computing device of claim 7, the actions further comprising:

generating, by the computing device and based on the set of facial feature descriptors, a quality score of the first face.

9. The computing device of claim 8 where the quality score is determined based partially on the location of the first face within the first image.

10. The computing device of claim 8 where the quality score is based partially on the amount of the first face in the first image.

11. The computing device of claim 7, the actions further comprising:

generating, by the computing device and based on the set of facial feature descriptors, an expression of the first face.

12. The computing device of claim 7, the actions further comprising:

generating, by the computing device and based on the set of facial feature descriptors, a pose of the first face.

13. At least one computer-readable media storing computer-executable instructions that, when executed by a computing device, cause the computing device to perform actions comprising:

assigning a face identifier to a first face detected in a first image, the first face belonging to a person;

generating, by the computing device, a set of facial feature descriptors based on an analysis of the first face detected in the first image and on the face identifier of the first face, each of the facial feature descriptors corresponding to an analyzed physical feature of the first face detected in the first image; and

generating, by the computing device and based on the set of facial feature descriptors, a face signature that uniquely identifies a second face detected in a second image as belonging to the same person.

14. The at least one computer-readable media of claim 13, the actions further comprising:

generating, by the computing device and based on the set of facial feature descriptors, a quality score of the detected face.

15. The at least one computer-readable media of claim 14 where the quality score is determined based partially on the location of the first face within the first image.

16. The at least one computer-readable media of claim 14 where the quality score is based partially on the amount of the first face in the first image.

17. The at least one computer-readable media of claim 13, the actions further comprising:

generating, by the computing device and based on the set of facial feature descriptors, an expression of the first face.

18. The at least one computer-readable media of claim 13, the actions further comprising:

generating, by the computing device and based on the set of facial feature descriptors, a pose of the first face.