US 12,265,599 B2
System and method for biometric-based authentication via CNN with linear activation and max pooling
Li Zhinong, Alpharetta, GA (US); and Xiaowu Zhang, Alpharetta, GA (US)
Assigned to ARMATURA LLC, Alpharetta, GA (US)
Filed by ARMATURA LLC, Alpharetta, GA (US)
Filed on Sep. 2, 2022, as Appl. No. 17/902,141.
Prior Publication US 2024/0078299 A1, Mar. 7, 2024
Int. Cl. G06F 21/32 (2013.01); G06V 40/12 (2022.01)
CPC G06F 21/32 (2013.01) [G06V 40/1365 (2022.01)] 21 Claims
OG exemplary drawing
 
1. A method implemented on at least one processor, a memory, and a communication platform enabling connection to a network for biometric based authentication, comprising:
receiving an input image representing biometric information of a person to be authenticated;
generating a feature vector of the input image based on the biometric information captured in the input image via a convolution neural network (CNN) that is realized using one or more linear activation functions, comprising a parametric rectified linear unit (PReLU) activation function and a flexible rectified linear unit (FReLU) activation function; and
authenticating the person based on the feature vector in accordance with a biometric-based recognition model.