US 11,657,649 B2
Classification of subjects within a digital image
Sourabh Gupta, Noida (IN); Saurabh Gupta, Noida (IN); and Ajay Bedi, Pradesh (IN)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Jan. 13, 2022, as Appl. No. 17/575,469.
Application 17/575,469 is a continuation of application No. 16/664,754, filed on Oct. 25, 2019, granted, now 11,256,907.
Prior Publication US 2022/0139108 A1, May 5, 2022
Int. Cl. G06V 40/16 (2022.01); G06T 7/246 (2017.01)
CPC G06V 40/172 (2022.01) [G06T 7/246 (2017.01); G06V 40/171 (2022.01); G06V 40/176 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
accessing image data from at least a first point in time and a second point in time, the image data comprising information associated with a set of subjects;
determining, for each subject in the set of subjects, a respective objective difference value between the first point in time and the second point in time based on one or more of:
(a) a first facial expression of the subject at the first point in time and a second facial expression of the subject at the second point in time, the first facial expression and the second facial expression determined using a first trained machine learning model, or
(b) a first outline contour of the subject at the first point in time and a second outline contour of the subject at the second point in time, the first outline contour and the second outline contour determined using a second trained machine learning model;
comparing, to an objective difference threshold, the respective objective difference value for each subject in the set of subjects; and
identifying a subset of active subjects from the set of subjects, based on the respective objective difference value of each active subject in the subset of active subjects exceeding the objective difference threshold.