Systems and methods for modifying an image in a video feed
View Patent ↗Systems and method for modifying an image in a video feed are described. In some aspects, a plurality of images are received from a plurality of client computing devices. Each image within the plurality of images includes a face. The plurality of images are modified according to a baseline face position and a baseline face size. At least a portion of the modified plurality of images are provided for display to at least one of the plurality of client computing devices.
1. A computer-implemented method for modifying an image, the method comprising:
receiving, from a plurality of client computing devices, a plurality of images, each image within the plurality of images comprising a face;
modifying the plurality of images according to a baseline face position and a baseline face size, wherein the baseline face position comprises a face position in a first image within the plurality of images, and wherein the baseline face size comprises a face size in the first image; and
providing, to at least one of the plurality of client computing devices, at least a portion of the modified plurality of images for display.
2. The method of claim 1 , wherein modifying the plurality of images according to the baseline face position and the baseline face size comprises:
setting a face position in each image of the plurality of images to the baseline face position; and
setting a face size in each image of the plurality of images to the baseline face size.
3. The method of claim 1 , further comprising:
setting a white balance in each image of the plurality of images to a baseline white balance.
4. The method of claim 1 , further comprising:
setting a contrast in each image of the plurality of images to a baseline contrast.
5. The method of claim 1 , wherein the plurality of images comprise images from video feeds.
6. The method of claim 5 , wherein modifying the plurality of images comprises modifying the video feeds.
7. The method of claim 6 , wherein the video feeds are modified according to the baseline face position and the baseline face size once per threshold time period.
8. The method of claim 1 , wherein the baseline face position comprises a predetermined face position, and wherein the baseline face size comprises a predetermined face size.
9. The method of claim 1 , further comprising:
determining the baseline face position and the baseline face size.
10. The method of claim 1 , wherein the first image comprises an image within the plurality of images having a largest face size among the plurality of images.
11. The method of claim 1 , wherein the baseline face position comprises a baseline eye position.
12. The method of claim 1 , further comprising:
modifying the plurality of images according to a baseline face tilt.
13. The method of claim 1 , wherein each image within the plurality of images comprises a background, the method further comprising:
replacing, with a default background, the background of each of the plurality of images.
14. A non-transitory computer-readable medium for modifying an image, the computer-readable medium comprising instructions which, when executed by one or more computers, cause the one or more computers to implement a method, the method comprising:
receiving, from a plurality of client computing devices, a plurality of images, each image within the plurality of images comprising a face;
modifying the plurality of images according to a baseline face position and a baseline face size, wherein the baseline face position comprises a face position in a first image within the plurality of images, and wherein the baseline face size comprises a face size in the first image; and
providing, to at least one of the plurality of client computing devices, at least a portion of the modified plurality of images for display.
15. The computer-readable medium of claim 14 , wherein the plurality of images comprise images from video feeds.
16. The computer-readable medium of claim 15 , wherein modifying the plurality of images comprises modifying the video feeds.
17. The computer-readable medium of claim 16 , wherein the video feeds are modified according to the baseline face position and the baseline face size once per threshold time period.
18. The computer-readable medium of claim 14 , wherein the baseline face position comprises a predetermined face position, and wherein the baseline face size comprises a predetermined face size.
19. A system for modifying an image, the system comprising:
one or more processors; and
a memory comprising instructions which, when implemented by the one or more processors, cause the one or more processors to implement a method, the method comprising:
receiving, from a plurality of client computing devices, a plurality of images, each image within the plurality of images comprising a face;
modifying the plurality of images according to a baseline face position and a baseline face size, wherein the baseline face position comprises a face position in a first image within the plurality of images, and wherein the baseline face size comprises a face size in the first image; and
providing, to at least one of the plurality of client computing devices, at least a portion of the modified plurality of images for display.
20. A computer-implemented method for modifying an image, the method comprising:
receiving, from a plurality of client computing devices, a plurality of images, each image within the plurality of images comprising a face of a corresponding participant in an online meeting;
determining a selected one of the plurality of images by, at least in part, selecting one of the plurality of images having a face with a largest size of the faces in the plurality of images;
determining a baseline face size in response to the selected one of the plurality of images by, at least in part, setting the baseline face size equal to the size of the face in the selected one of the plurality of images;
modifying the plurality of images according to a baseline face position and the baseline face size; and
providing, to at least one of the plurality of client computing devices, at least a portion of the modified plurality of images for display.
21. The method of claim 20 , wherein determining the selected one of the plurality of images further includes selecting one of the plurality of images including a face having a most centered position of the faces in the plurality of images, and further comprising:
determining the baseline face position in response to the selected one of the plurality of images by, at least in part, setting the baseline face position equal to the position of the face in the selected one of the plurality of images.
22. The method of claim 21 , further comprising:
determining a baseline face tilt in response to the selected one of the plurality of images by setting the baseline face tilt to a face tilt of the face in the selected one of the plurality of images; and
modifying the face in each of the plurality of images according to the baseline face tilt.
23. A computer-implemented method for modifying an image, the method comprising:
receiving, from a plurality of client computing devices, a plurality of images, each image within the plurality of images comprising a face of a corresponding participant in an online meeting;
deriving a baseline face size from a size of a face in a first one of the plurality of images;
modifying the plurality of images according to a baseline face position and the baseline face size, wherein modifying the plurality of images according to the baseline face size includes modifying a size of a face in a second one of the plurality of images to match the size of the face in the first one of the plurality of images; and
providing, to at least one of the plurality of client computing devices, at least a portion of the modified plurality of images for display.