US 12,405,716 B2
Systems and methods for automatic formatting of images for media assets based on user profile
Aaron Peter Blohowiak, Belmont, CA (US); Walter R. Klappert, North Hollywood, CA (US); Michael R. Nichols, La Canada Flintridge, CA (US); and Olivier Chalouhi, Mountain View, CA (US)
Assigned to Adeia Guides Inc., San Jose, CA (US)
Filed by Adeia Guides Inc., San Jose, CA (US)
Filed on Nov. 2, 2023, as Appl. No. 18/500,928.
Application 18/500,928 is a continuation of application No. 17/949,663, filed on Sep. 21, 2022, granted, now 11,842,040.
Application 17/949,663 is a continuation of application No. 16/816,094, filed on Mar. 11, 2020, granted, now 11,481,095, issued on Oct. 25, 2022.
Application 16/816,094 is a continuation of application No. 14/752,031, filed on Jun. 26, 2015, granted, now 10,628,009, issued on Apr. 21, 2020.
Prior Publication US 2024/0152260 A1, May 9, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 3/04845 (2022.01); G06F 3/0481 (2022.01); G06F 3/04842 (2022.01); G06F 3/14 (2006.01); G06F 16/78 (2019.01); G06T 11/60 (2006.01); G09G 5/00 (2006.01); G09G 5/14 (2006.01)
CPC G06F 3/04845 (2013.01) [G06F 3/0481 (2013.01); G06F 3/04842 (2013.01); G06F 3/14 (2013.01); G06F 3/1415 (2013.01); G06F 16/78 (2019.01); G06T 11/60 (2013.01); G09G 5/003 (2013.01); G09G 5/14 (2013.01); G06T 2210/22 (2013.01); G09G 2320/08 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method for selectively generating for display portions of an image, the method comprising:
identifying an image corresponding to a requested media asset, wherein the image comprises a plurality of portions, and wherein each portion of the plurality of portions comprises a respective depiction of a person;
determining a level of prevalence of each respective person in the requested media asset, wherein the level of prevalence corresponds to a relative amount of time the respective person is present in the requested media asset;
determining a target aspect ratio;
determining, based on the target aspect ratio, a target number of portions of the plurality of portions;
identifying a plurality of selected portions based on the target number of portions and the respective level of prevalence of each person corresponding to the plurality of portions;
cropping out each of the plurality of selected portions, wherein at least two of the plurality of selected portions are non-adjacent portions of the plurality of portions;
stitching the plurality of selected portions together to generate a stitched image; and
generating for display, the stitched image.