System, method, and computer program for determining an exposure based on skin tone

Patent metadata

Field	Value
Publication number	US-10372971-B2
Application number	US-201816215351-A
Country	US
Kind code	B2
Filing date	Dec 10, 2018
Priority date	Oct 5, 2017
Publication date	Aug 6, 2019
Grant date	Aug 6, 2019

Abstract

A system and method are provided for capturing an image with correct skin tone exposure. In use, one or more faces are detected having threshold skin tone within a scene. Next, based on the detected one or more faces, the scene is segmented into one or more face regions and one or more non-face regions. Next, one or more images of the scene are captured. Further, in response to the capture, the one or more face regions are processed to generate a final image.

First claim

What is claimed is:

1. A device, comprising:
a non-transitory memory storing instructions;
a camera module; and
one or more processors in communication with the non-transitory memory and the camera module, wherein the one or more processors execute the instructions to:
detect one or more faces having threshold skin tone within a scene;
based on the detected one or more faces, segment the scene into one or more face regions and one or more non-face regions;
cause the camera module to capture two or more images of the scene, wherein a first image of the two or more images is exposed so that a median intensity of the one or more face regions defines a mid-point intensity of the first image, and a second image of the two or images is exposed so that a median intensity of the one or more non-face regions defines a mid-point intensity of the second image; and
in response to the capture, process the one or more face regions to generate a final image.

2. The device of claim 1 , wherein the threshold skin tone is a predefined average intensity or histogram median.

3. The device of claim 2 , wherein the predefined average intensity or histogram median is based on the one or more face regions.

4. The device of claim 1 , wherein the device is operable such that the two or more images include at least one high dynamic range (HDR) image.

5. The device of claim 1 , wherein the device is operable such that the processing includes processing the one or more non-face regions and applying an HDR effect by blending, using a strength coefficient, the first image and the second image.

6. The device of claim 1 , wherein the device is operable such that the capturing is of a video stream.

7. The device of claim 1 , wherein the device is operable such that the processing includes applying a local equalization on pixels within the one or more face regions.

8. The device of claim 1 , wherein the device is operable such that a model is constructed of one or more individuals depicted within the scene based on a depth map and at least one visual image.

9. The device of claim 8 , wherein the depth map is used to construct a three-dimensional (3D) model of the one or more faces.

10. The device of claim 8 , wherein the at least one visual image includes a surface texture.

11. The device of claim 10 , wherein the surface texture includes one or more features associated with each of the one or more faces.

12. The device of claim 1 , wherein the device is operable such that the segmenting includes a transition region between the one or more face regions and the one or more non-face regions.

13. The device of claim 1 , wherein the device is operable such that the one or more face regions includes at least one of a depth map, and a texture map.

14. The device of claim 13 , wherein the device is operable such that a lighting gradient is used to modify post-processing lighting conditions on the one or more faces.

15. The device of claim 1 , wherein the device is operable to further execute the instructions to correct a color of light associated with skin tone associated with each of the one or more faces based on a measurement of an ambient lighting color balance.

16. The device of claim 1 , wherein the device is operable to further execute the instructions to create a texture map which selectively modifies contrast of the scene to correct for skin tone associated with each of the one or more faces.

17. The device of claim 1 , wherein the device is operable such that a histogram associated with the final image shows correct exposure data for the scene.

18. A computer-implemented method, comprising:
detecting, using a processor, one or more faces having threshold skin tone within a scene;
based on the detected one or more faces, segmenting, using the processor, the scene into one or more face regions and one or more non-face regions;
capturing, using a camera, two or more images of the scene, wherein a first image of the two or more images is exposed so that a median intensity of the one or more face regions defines a mid-point intensity of the first image, and a second image of the two or images is exposed so that a median intensity of the one or more non-face regions defines a mid-point intensity of the second image; and
in response to the capturing, processing, using the processor, the one or more face regions to generate a final image.

19. A computer program product comprising computer executable instructions stored on a non-transitory computer readable medium that when executed by a processor instruct the processor to:
detect one or more faces having threshold skin tone within a scene;
based on the detected one or more faces, segment the scene into one or more face regions and one or more non-face regions;
cause a camera module to capture two or more images of the scene, wherein a first image of the two or more images is exposed so that a median intensity of the one or more face regions defines a mid-point intensity of the first image, and a second image of the two or images is exposed so that a median intensity of the one or more non-face regions defines a mid-point intensity of the second image; and
in response to the capture, process the one or more face regions to generate a final image.

Assignees

• Duelight Llc

Inventors

• Rivard William Guie
• Kindle Brian J
• Feder Adam Barry

Classifications

• G06V40/168

  Feature extraction; Face representation · CPC title

• G06T2207/20208

  High dynamic range [HDR] image processing · CPC title

• G06T2207/20012

  Locally adaptive · CPC title

• G06T2207/10024

  Color image · CPC title

• G06T2207/30201

  Face · CPC title