US 11,881,006 B2
Machine learning assistant for image analysis
Peter Wilczynski, San Francisco, CA (US); Joules Nahas, Mountain View, CA (US); Anthony Bak, San Francisco, CA (US); John Carrino, Menlo Park, CA (US); David Montague, East Palo Alto, CA (US); Daniel Zangri, Palo Alto, CA (US); Ernest Zeidman, Palo Alto, CA (US); and Matthew Elkherj, Palo Alto, CA (US)
Assigned to Palantir Technologies Inc., Denver, CO (US)
Filed by Palantir Technologies Inc., Denver, CO (US)
Filed on May 26, 2022, as Appl. No. 17/826,006.
Application 17/826,006 is a continuation of application No. 16/523,932, filed on Jul. 26, 2019, granted, now 11,347,971.
Application 16/523,932 is a continuation of application No. 16/128,266, filed on Sep. 11, 2018, granted, now 10,410,090, issued on Sep. 10, 2019.
Claims priority of provisional application 62/721,935, filed on Aug. 23, 2018.
Prior Publication US 2022/0284241 A1, Sep. 8, 2022
Int. Cl. G06V 10/44 (2022.01); G06F 18/214 (2023.01); G06V 10/776 (2022.01); G06V 10/778 (2022.01); G06V 20/10 (2022.01)
CPC G06V 10/44 (2022.01) [G06F 18/2148 (2023.01); G06V 10/776 (2022.01); G06V 10/7788 (2022.01); G06V 20/176 (2022.01)] 18 Claims
OG exemplary drawing
 
1. A system comprising:
one or more processors;
memory storing instructions that, when executed by the one or more processors, cause the system to perform:
obtaining an image, the image including a depiction of one or more objects;
receiving a marking of a set of pixel representations within the image, the set of pixel representations being positioned within or near the one or more objects, wherein the marking comprises a first portion associated with a first source and a second portion associated with a second source, and the first portion and the second portion are weighed differently based on previous accuracy or confidence levels corresponding to the first source and the second source; and
labeling a first object within the image based on a type of pixel representation corresponding to the first object.