A CNN model, a CNN training method and a CNN-based vein recognition method

Abstract

The invention discloses a CNN model, a CNN training method and a CNN-based vein recognition method. The CNN model includes a plurality of convolutional layers, a fully connected layer and a SoftMax layer; The biometric database of the feature is used to train the model; the fully connected layer and the SoftMax layer are used as a multi-class classifier; a multi-class neural network is trained to learn the characteristics that can distinguish the vein category; after the training is completed, The output of the previous layer of the fully connected layer is used as a feature, and the similarity of a pair of images is measured by calculating the cosine distance of these features. The invention integrates the multimodal biometric database for training the network, solves the problem of insufficient training samples, and can greatly improve the retrieval speed in a super-large identity authentication database.

Description

technical field [0001] The invention relates to the technical field of deep learning and vein recognition, in particular to a CNN model, a CNN training method and a CNN-based vein recognition method. Background technique [0002] With the development of science and technology, biometric identification technology has gradually replaced traditional identity authentication methods in some aspects, making people's lives more and more convenient, especially the finger vein identification technology has attracted more and more attention from researchers. Because veins are located under the skin, unlike fingerprints, they are not easily damaged by external factors, and because they are invisible to the naked eye, they are difficult to be stolen and forged, so they have extremely high stability and security. In addition, the device of finger veins is light and convenient, which makes finger vein recognition technology have great application prospects. However, there are still many p...

AI Technical Summary

Problems solved by technology

However, due to the problem of imaging equipment, vein images are generally blurred. This type of method will encounter problems similar to those based on minutiae features: the features extracted from blurred images are not stable enough.

However, due to the lack of databases available in the field of finger vein recognition, the application of deep learning in this field is limited.

Some people first tried some deep learning algorithms in the field of finger veins, but because the database is too small, its performance is not very ideal

Images