US 11,055,566 B1
Utilizing a large-scale object detector to automatically select objects in digital images
Khoi Pham, Hyattsville, MD (US); Scott Cohen, Sunnyvale, CA (US); Zhe Lin, Fremont, CA (US); Zhihong Ding, Fremont, CA (US); and Walter Wei Tuh Chang, San Jose, CA (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Mar. 12, 2020, as Appl. No. 16/817,418.
Int. Cl. G06K 9/00 (2006.01); G06K 9/62 (2006.01)
CPC G06K 9/623 (2013.01) [G06K 9/6259 (2013.01); G06K 9/6261 (2013.01)] 20 Claims
OG exemplary drawing
1. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computing device to:
in response to receiving a query string indicating a query object to select within a digital image, generate a plurality of region proposals for potential objects in the digital image;
filter the plurality of region proposals to identify a subset of filtered region proposals;
generate one or more object labels for each filtered region proposal of the subset of filtered region proposals utilizing an auto tagging model; and
detect the query object from the subset of filtered region proposals based on the one or more object labels.