US 11,921,831 B2
Enrollment system with continuous learning and confirmation
Krishna Khadloya, San Jose, CA (US); and Manuel Gonzalez, San Jose, CA (US)
Assigned to INTELLIVISION TECHNOLOGIES CORP, San Jose, CA (US)
Filed by INTELLIVISION TECHNOLOGIES CORP, San Jose, CA (US)
Filed on Mar. 12, 2021, as Appl. No. 17/200,584.
Prior Publication US 2022/0292170 A1, Sep. 15, 2022
Int. Cl. G06F 21/32 (2013.01); G06F 18/22 (2023.01); G06N 3/08 (2023.01); G06V 20/56 (2022.01); G06V 40/16 (2022.01)
CPC G06F 21/32 (2013.01) [G06F 18/22 (2023.01); G06N 3/08 (2013.01); G06V 20/56 (2022.01); G06V 40/172 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A method for authentication, the method comprising:
receiving reference image information about a target object;
receiving a test image including information about a candidate object;
determining a relatedness metric indicating a magnitude of relatedness of the target object and the candidate object; and
based on a value of the relatedness metric, at least one of:
generating updated reference image information using the test image; and
providing a validation request to an administrator, the validation request including one or more of the relatedness metric, information about the target object, and information about the candidate object, wherein the validation request is provided to the administrator when the relatedness metric indicates at least a specified minimum threshold amount of dissimilarity between the target object and the candidate object.