US 12,260,557 B2
Object selection for images using image regions
Zijun Wei, San Jose, CA (US); Yilin Wang, Sunnyvale, CA (US); Jianming Zhang, Fremont, CA (US); and He Zhang, Santa Clara, CA (US)
Assigned to adobe inc., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Jun. 13, 2022, as Appl. No. 17/838,995.
Prior Publication US 2023/0401718 A1, Dec. 14, 2023
Int. Cl. G06K 9/00 (2022.01); G06T 7/11 (2017.01); G06T 7/136 (2017.01); G06V 10/46 (2022.01); G06V 10/764 (2022.01)
CPC G06T 7/11 (2017.01) [G06T 7/136 (2017.01); G06V 10/462 (2022.01); G06V 10/764 (2022.01)] 16 Claims
OG exemplary drawing
 
1. One or more computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform operations, the operations comprising:
processing an image to identify a first region having a first object and a second region having a second object and to determine a first classification for the first region and a second classification for the second region;
selecting, from a plurality of masking pipelines, a first masking pipeline for the first region based on the first classification for the first region and a second masking pipeline for the second region based on the second classification for the second region;
generating a first region mask selecting portions of the first region with the first object by using the first masking pipeline to process the first region that is a first portion of the image comprising less than the entire image;
generating a second region mask selecting portions of the second region with the second object by using the second masking pipeline to process the second region that is a second portion of the image different from the first portion and comprising less than the entire image; and
generating an image mask for the image by combining the first region mask for the first region and the second region mask for the second region.