Finger vein anti-counterfeiting identification method and system based on autoencoder

Abstract

The self-encoder-based finger vein anti-counterfeit identification method and system provided by the embodiments of the present invention belong to the technical field of biological feature identification. The finger vein anti-counterfeiting identification method based on autoencoder first establishes a training set based on the collected finger vein images and their corresponding labels. Second, construct a sparse autoencoder model and train it with a training set of grayscale images. Then, initialize the neural network with the weights of the trained SAE and train it. The output of each hidden layer of the neural network is used as the extracted feature vector. Finally, each feature vector is input to the random forest classifier, and the output results are fused with the Bayesian model to realize the identification of the authenticity of the finger veins.

Description

technical field [0001] The present invention relates to the technical field of biological feature identification, in particular to a finger vein anti-counterfeit identification method and system based on an autoencoder. Background technique [0002] The rapid development of information technology makes information security more and more important, which also means that higher and higher information security protection is required. As an emerging biometric technology, vein-based biometrics have attracted widespread attention in the field of biometrics. Compared with traditional biometric technologies, such as fingerprints, palm prints, iris, and face recognition, vein recognition technology has the advantages of low cost, easy data collection and non-contact operation. In addition, because the veins are located inside the living body, they are difficult to steal and counterfeit, and are less susceptible to changes in the surface skin, so they have higher security performance...

AI Technical Summary

Problems solved by technology

There are many finger vein anti-counterfeiting identification algorithms, such as Binarized Statistical Image Feature (BSIF), Rice Transform (RT), Local Binary Pattern (LBP), Local Phase Quantization (LPQ), but they use manual descriptor pairs Therefore, there are the following disadvantages in the prior art: (1) It is difficult to prove that the manually extracted features must be related to the authenticity of the finger vein image

(2) Even if there are features to distinguish the authenticity of the image, it is difficult to establish an effective mathematical model to describe them

Images