US 12,073,565 B2
Generating synthetic images as training dataset for a machine learning network
Reza Farivar, Champaign, IL (US); and Kenneth Taylor, Champaign, IL (US)
Assigned to Capital One Services, LLC, McLean, VA (US)
Filed by Capital One Services, LLC, McLean, VA (US)
Filed on Dec. 23, 2022, as Appl. No. 18/145,880.
Application 18/145,880 is a continuation of application No. 17/249,378, filed on Mar. 1, 2021, granted, now 11,538,171.
Application 17/249,378 is a continuation of application No. 16/407,752, filed on May 9, 2019, granted, now 10,937,171, issued on Mar. 2, 2021.
Application 16/407,752 is a continuation of application No. 15/963,742, filed on Apr. 26, 2018, granted, now 10,332,261, issued on Jun. 25, 2019.
Prior Publication US 2023/0206460 A1, Jun. 29, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 7/149 (2017.01); G06N 3/08 (2023.01); G06N 3/088 (2023.01); G06N 20/00 (2019.01); G06T 7/11 (2017.01); G06T 7/174 (2017.01); G06T 7/194 (2017.01)
CPC G06T 7/149 (2017.01) [G06N 3/08 (2013.01); G06N 3/088 (2013.01); G06N 20/00 (2019.01); G06T 7/11 (2017.01); G06T 7/174 (2017.01); G06T 7/194 (2017.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30176 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method, comprising:
applying, by a device, a deformation to an image;
generating, by the device, a deformed image based on applying the deformation to the image;
applying, by the device, the deformation to a mask image that identifies a target location in the image;
generating, by the device, a deformed mask image based on applying the deformation to the mask image; and
training, by the device, a model using the deformed image and the deformed mask image.