A finger vein image recognition method based on fusion of local coding and a CNN model

Abstract

A finger vein image recognition method based on fusion of local coding and CNN model is proposed. The method comprises the following steps: extracting the finger vein image from the finger vein image;using the encoder based on weighted symmetric local graph structure to encode the image: the reconstructed encoded convolutional filter is obtained; establishing an improved convolution neural network mode; performing feature extraction of a digital vein ROI image; measuring the similarity of the ROI images of digital veins to be matched. The finger vein image recognition method integrating the local coding and the CNN model provided by the invention can not only solve the problem of variable finger posture to a certain extent; experimental results on two finger vein databases show that the proposed method is feasible to some extent, which not only has good matching effect, but also reduces the number of parameters that can be learned, reduces the learning cost and improves the matching efficiency.

Description

technical field [0001] The invention belongs to the technical field of finger vein image recognition, in particular to a finger vein image recognition method that integrates local coding and a CNN model. Background technique [0002] With the rapid development of computer technology and the advent of the information age, traditional biometric identification technology can no longer meet people's needs, and people's requirements for the accuracy of identification technology are getting higher and higher. Compared with other biometric identification technologies (such as: face, fingerprint, iris and palm print, etc.), finger vein has the advantages of vitality, uniqueness, user-friendliness and long-term invariance. In addition, since the finger vein is located under the skin, the image of the finger vein is usually collected using near-infrared (NIR) imaging, so the finger vein is non-contact and difficult to be copied and forged. In recent years, finger vein recognition tec...

AI Technical Summary

Problems solved by technology

[0003] Due to the large number of learnable parameters of the existing convolutional neural network model, the learning cost of the network model is high, and there may be a problem of overfitting

At present, people usually directly reduce the number of parameters of the neural network structure to reduce the learning cost, but this may cause the network performance to decrease accordingly.

Images