US 11,810,396 B2
Image annotation using prior model sourcing
Matthew Shreve, Campbell, CA (US); Raja Bala, Pittsford, NY (US); and Jeyasri Subramanian, Sunnyvale, CA (US)
Assigned to Xerox Corporation, Norwalk, CT (US)
Filed by PALO ALTO RESEARCH CENTER INCORPORATED, Palo Alto, CA (US)
Filed on Apr. 16, 2021, as Appl. No. 17/233,365.
Prior Publication US 2022/0335239 A1, Oct. 20, 2022
Int. Cl. G06F 16/535 (2019.01); G06V 40/16 (2022.01); G06F 16/58 (2019.01); G06F 16/55 (2019.01); G06F 16/538 (2019.01); G06F 18/214 (2023.01); G06V 10/774 (2022.01)
CPC G06V 40/169 (2022.01) [G06F 16/535 (2019.01); G06F 16/538 (2019.01); G06F 16/55 (2019.01); G06F 16/5866 (2019.01); G06F 18/214 (2023.01); G06V 10/774 (2022.01); G06V 40/164 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A method of image annotation comprising:
selecting a plurality of annotation models related to an annotation task for an image;
obtaining a candidate annotation map for the image from each of the plurality of annotation models;
selecting a first candidate annotation map from the candidate annotation maps, the first candidate annotation map to be displayed via a user interface of a client device, wherein each of the candidate annotation maps comprises suggested annotations for the image;
receiving, by a processing device, a first set of user selections or modifications of at least one of the suggested annotations from the first candidate annotation map;
selecting, from the candidate annotation maps, a second candidate annotation map to be displayed thereafter via the interface of the client device, the second candidate annotation map comprising additional suggested annotations for the image;
receiving a second set of user selections or modifications of at least one of the additional suggested annotations; and
generating, by the processing device, a final annotation map based on the first set of user selections or modifications from the first candidate annotation map and the second set of user selections or modifications from the second candidate annotation map.