US 12,223,657 B2
Image segmentation system
Menglei Chai, Los Angeles, CA (US); David LeMieux, Hermosa Beach, CA (US); Shubham Vij, Los Angeles, CA (US); and Ian Wehrman, Santa Monica, CA (US)
Assigned to Snap Inc., Santa Monica, CA (US)
Filed by Snap Inc., Santa Monica, CA (US)
Filed on Apr. 18, 2023, as Appl. No. 18/136,212.
Application 18/136,212 is a continuation of application No. 17/249,445, filed on Mar. 2, 2021, granted, now 11,663,723.
Application 17/249,445 is a continuation of application No. 16/365,228, filed on Mar. 26, 2019, granted, now 10,964,023.
Prior Publication US 2023/0252639 A1, Aug. 10, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/11 (2017.01); G06F 3/04845 (2022.01); G06T 7/12 (2017.01); G06T 7/13 (2017.01); G06T 7/174 (2017.01); G06T 7/194 (2017.01); G06V 10/56 (2022.01)
CPC G06T 7/11 (2017.01) [G06F 3/04845 (2013.01); G06T 7/12 (2017.01); G06T 7/13 (2017.01); G06T 7/174 (2017.01); G06T 7/194 (2017.01); G06V 10/56 (2022.01); G06T 2207/20104 (2013.01); G06T 2207/20132 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
causing display of an image within a graphical user interface at a client device, the image comprising a display of an object, a background, and a foreground;
receiving an input that identifies a portion of the image that corresponds with the foreground of the image;
causing display of a visual representation of the input;
identifying a boundary of the display of the object depicted within the foreground of the image based on a position of the visual representation of the input;
cropping the object from the image based on the boundary of the object; and
generating a media object based on the object, the media object comprising a shape based on the boundary of the object.