US 12,455,941 B2
Systems and methods for facial recognition training dataset adaptation with limited user feedback in surveillance systems
Xihua Dong, San Jose, CA (US)
Assigned to Fortinet, Inc., Sunnyvale, CA (US)
Filed by Fortinet, Inc., Sunnyvale, CA (US)
Filed on May 20, 2021, as Appl. No. 17/325,943.
Prior Publication US 2022/0374656 A1, Nov. 24, 2022
Int. Cl. G06K 9/62 (2022.01); G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06N 5/04 (2023.01); G06N 20/00 (2019.01); G06V 40/16 (2022.01); G06V 20/52 (2022.01)
CPC G06F 18/2148 (2023.01) [G06F 18/2178 (2023.01); G06F 18/2413 (2023.01); G06N 5/04 (2013.01); G06N 20/00 (2019.01); G06V 40/172 (2022.01); G06V 20/52 (2022.01)] 17 Claims
OG exemplary drawing
 
1. A facial recognition system, the system comprising:
a processing resource;
a non-transitory computer-readable medium, having stored therein: (a) a training dataset including a plurality of samples of image features that correspond to an individual, wherein each sample in the training dataset includes a respective sample score; and (b) instructions that when executed by the processing resource cause the processing resource to:
receive an input image;
receive a match score indicating a correspondence of the input image to a first sample in the training dataset;
receive a user feedback about a label of the input image;
modify the score corresponding to the first sample, the modification including:
incrementing the score by a first value if the user feedback on the label of the input image is equal to a label of the first sample; or
decrementing the score by the first value if the user feedback on the label of the input image is not equal to the label of the first sample; and
remove lower scored samples from the training dataset to reduce computational complexity of facial recognition.