US 11,854,116 B2
Task-based image masking
Vivek Yadav, Issaquah, WA (US); Aayush Gupta, Seattle, WA (US); Yue Wu, Torrance, CA (US); Pradeep Natarajan, Chicago, IL (US); and Ayush Jaiswal, Los Angeles, CA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on May 10, 2022, as Appl. No. 17/740,533.
Application 17/740,533 is a continuation of application No. 16/913,837, filed on Jun. 26, 2020, granted, now 11,334,773.
Prior Publication US 2022/0405528 A1, Dec. 22, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 11/00 (2006.01); G06N 20/00 (2019.01); G06N 3/08 (2023.01); G06F 18/2431 (2023.01); G06F 18/214 (2023.01); G06V 10/772 (2022.01); G06V 10/20 (2022.01)
CPC G06T 11/00 (2013.01) [G06F 18/214 (2023.01); G06F 18/2431 (2023.01); G06N 3/08 (2013.01); G06N 20/00 (2019.01); G06V 10/20 (2022.01); G06V 10/772 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving first image data representing a first image, the first image comprising a first image portion representing a first type of object and a second image portion;
processing the first image data using a first machine learning component corresponding to a first image processing operation to determine second image data, the second image data comprising:
a first data portion corresponding to the first image portion, and
a second data portion representing an obfuscated version of the second image portion; and
performing the first image processing operation using the second image data to determine output data.