US 12,260,598 B2
Learning-based image compression setting
Jonathan D. Hurwitz, San Jose, CA (US); and Punyabrata Ray, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Appl. No. 17/420,875
Filed by Google LLC, Mountain View, CA (US)
PCT Filed Jun. 13, 2020, PCT No. PCT/US2020/037646
§ 371(c)(1), (2) Date Jul. 6, 2021,
PCT Pub. No. WO2021/251988, PCT Pub. Date Dec. 16, 2021.
Prior Publication US 2022/0053195 A1, Feb. 17, 2022
Int. Cl. G06T 9/00 (2006.01); G06F 18/214 (2023.01); G06N 3/04 (2023.01); G06V 10/40 (2022.01); G06V 10/70 (2022.01); G06V 10/778 (2022.01); H04N 19/136 (2014.01); H04N 19/162 (2014.01)
CPC G06T 9/002 (2013.01) [G06F 18/214 (2023.01); G06N 3/04 (2013.01); G06V 10/40 (2022.01); G06V 10/70 (2022.01); G06V 10/7784 (2022.01); G06V 10/7788 (2022.01); H04N 19/136 (2014.11); H04N 19/162 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
providing a first user interface to a user associated with a user account with two or more versions of a sample image, each compressed with a different compression setting;
obtaining user input from the user that identifies a particular version of the sample image from the two or more versions; and
selecting a baseline compression setting associated with the particular version of the sample image as a baseline for the user account;
obtaining an input image, the input image associated with the user account;
determining, using a feature-detection machine-learning model, one or more features of the input image including one or more regions of interest;
determining, using a user-specific machine-learning model personalized to the user account, a second compression setting for the input image based on the baseline compression setting and the one or more features in the input image by keeping the one or more regions of interest in the input image in high resolution and compressing a remaining portion of the input image; and
compressing the input image based on the second compression setting.