Finger vein verification method, electronic equipment and storage medium

Abstract

The invention discloses a finger vein verification method, electronic equipment and a storage medium, which are applied to a U-Net network architecture, and the method comprises the steps: obtaining afinger vein image, and carrying out the ROI extraction of the finger vein image; extracting vein lines through a method for detecting the local maximum curvature of the cross section of the finger vein, and obtaining a segmented image; carrying out differential calculation processing on any two segmented images to obtain a differential image so as to carry out data expansion; carrying out channelcopying on the difference image and then taking the difference image as input of a pre-training stage, and reserving an optimal weight of the pre-training stage as a pre-training weight of a cascadeoptimization stage pair; and performing channel superposition on the differential image and the two original segmented images to serve as input of the cascade optimization stage, optimizing parametersof a pre-trained network, and obtaining an optimized finger vein verification model.

Description

technical field [0001] The invention relates to the technical field of neural networks, in particular to a finger vein verification method, electronic equipment and a storage medium. Background technique [0002] As people's requirements for the security and accuracy of biometric systems are getting higher and higher, biometric technology has received more and more attention. As one of many biometric identification technologies, finger vein recognition has become a current research hotspot due to its advantages of non-contact acquisition, live detection, difficult forgery, and low cost. [0003] In recent years, the finger vein recognition method using convolutional neural network as the carrier has achieved excellent performance, thanks to the deep features learned by CNN (Convolutional Neural Networks, convolutional neural network) have good generalization and expression capabilities. At the same time, the network is constrained by limited public vein data resources, and ...

AI Technical Summary

Problems solved by technology

At the same time, the network is constrained by limited public vein data resources, and it is prone to overfitting. Although the vein segmentation task solves the problems of data shortage and class imbalance by dividing a large number of patches (small blocks), but in the verification task This strategy cannot be used because overlapping patches can deepen the network's understanding of vein patterns and facilitate the segmentation of finger veins, but repeated similar patches will increase the difficulty of verification, reducing inter-class differences and increasing intra-class differences

[0004] In addition, the feature expression of the network loses the structural correlation of the image, and cannot obtain all the information from the dimension, and as the network deepens, it will generate a large computational overhead

Images