Creation of representative content based on facial analysis

Patent metadata

Field	Value
Publication number	US-11295114-B2
Application number	US-201916388102-A
Country	US
Kind code	B2
Filing date	Apr 18, 2019
Priority date	Apr 28, 2014
Publication date	Apr 5, 2022
Grant date	Apr 5, 2022

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.

First claim

The invention claimed is:

1. A method performed on a computing device, the method comprising:
detecting a first face in a first image;
analyzing, by the computing device, features of the detected first face to generate a set of facial feature descriptors, wherein individual facial feature descriptors describe individual features that differ from features described by other facial feature descriptors in the set of facial feature descriptors, the set of facial feature descriptors comprising multiple facial feature descriptors that describe multiple features of the detected first face;
generating, by the computing device a face signature based on multiple distinct inputs, comprising: (1) individual ones of the multiple facial feature descriptors from the set of facial feature descriptors that were generated by the analyzing the features of the first face and (2) from the first image, corresponding individual ones of the multiple features of the first face that was detected in the first image by the detecting; and
identifying a face in a second image as being similar to the first face, at least within a scope of the analyzed features, based on the generated face signature.

2. The method of claim 1 where the generated face signature is sufficient to identify faces in other images that are of a same person as the detected face.

3. The method of claim 1 further comprising generating, by the computing device based on the analyzed features of the detected face, a quality score of the detected face.

4. The method of claim 3 where the quality score is influenced based on whether or not the detected face is located near an edge of the image.

5. The method of claim 3 where the quality score is influenced based on whether or not the detected face is cut off in the image.

6. The method of claim 1 further comprising generating, by the computing device based on the analyzed features of the detected face, an expression of the detected face.

7. The method of claim 1 further comprising generating, by the computing device based on the analyzed features of the detected face, a pose of the detected face.

8. 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:
detecting a first face in a first image;
analyzing, by the computing device, features of the detected first face to generate a set of facial feature descriptors, wherein individual facial feature descriptors describe individual features that differs from features described by other facial feature descriptors in the set of facial feature descriptors, the set of facial feature descriptors comprising multiple facial feature descriptors that describe multiple features of the detected first face
generating, by the computing device, a face signature based on multiple distinct inputs, comprising: (1) individual ones of the multiple facial feature descriptors from the set of facial feature descriptors that were generated by the analyzing the features of the first face and (2) from the first image, corresponding individual ones of the multiple features of the first face that was detected in the first image by the detecting; and
identifying a face in a second image as being similar to the first face at least within a scope of the analyzed features, based on the generated face signature.

9. The computing device of claim 8 where the generated face signature is sufficient to identify faces in other images that are of a same person as the detected face.

10. The computing device of claim 8 , the actions further comprising generating, by the computing device based on the analyzed features of the detected face, a quality score of the detected face.

11. The computing device of claim 10 where the quality score is influenced based on whether or not the detected face is located near an edge of the image.

12. The computing device of claim 10 where the quality score is influenced based on whether or not the detected face is cut off in the image.

13. The computing device of claim 8 , the actions further comprising generating, by the computing device based on the analyzed features of the detected face, an expression of the detected face.

14. The computing device of claim 8 , the actions further comprising generating, by the computing device based on the analyzed features of the detected face, a pose of the detected face.

15. 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:
detecting a first face in a first image;
analyzing, by the computing device, features of the detected first face to generate a set of facial feature descriptors, wherein individual facial feature descriptors describe individual features that differ from features described by other facial feature descriptors in the set of facial feature descriptors, the set of facial feature descriptors comprising multiple facial feature descriptors that describe multiple features of the detected first face;
generating, by the computing device a face signature based on multiple distinct inputs, comprising: (1) individual ones of the multiple facial feature descriptors from the set of facial feature descriptors that were generated by the analyzing the features of the first face and (2) from the first image, corresponding individual ones of the multiple features of the first face that was detected in the first image by the detecting; and
identifying a face in a second image as being similar to the first face, at least within a scope of the analyzed features, based on the generated face signature.

16. The at least one computer-readable media of claim 15 where the generated face signature is sufficient to identify faces in other images that are of a same person as the detected face.

17. The at least one computer-readable media of claim 15 , the actions further comprising generating, by the computing device based on the analyzed features of the detected face, a quality score of the detected face.

18. The at least one computer-readable media of claim 17 where the quality score is influenced based on whether or not the detected face is located near an edge of the image, or where the quality score is influenced based on whether or not the detected face is cut off in the image.

19. The at least one computer-readable media of claim 17 , the actions further comprising generating, by the computing device based on the analyzed features of the detected face, an expression of the detected face.

20. The at least one computer-readable media of claim 15 , the actions further comprising generating, by the computing device based on the analyzed features of the detected face, a pose of the detected face.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Lee David
• Chan Chunkit Jacky
• Ricard Doug
• Scott Stacia
• Light Allison

Classifications

• G06V40/168

  Feature extraction; Face representation · CPC title

• G06V40/16 Primary

  Human faces, e.g. facial parts, sketches or expressions · CPC title

• G06V40/174

  Facial expression recognition · CPC title

• C07C1/00

  Preparation of hydrocarbons from one or more compounds, none of them being a hydrocarbon · CPC title

• G06V40/193

  Preprocessing; Feature extraction · CPC title