Finger vein recognition method based on fusion local and global feature network

Abstract

The invention discloses a finger vein recognition method based on a fusion local and global feature network. The method comprises the following steps: S1, constructing a training data set, collecting a plurality of user finger images Ibasic as a basic training set, expanding the basic training set Ibasic, and performing normalization processing to obtain a training data set Itrain; s2, designing a finger vein feature extraction network based on fusion of local and global features; s3, designing a network loss function; s4, training the whole model until the whole training set is iteratively trained for a plurality of times; and S5, inputting the test set image into the trained model to extract finger vein features, and performing 1: 1 comparison recognition by adopting an Euclidean distance. Compared with the prior art, the extracted finger vein features are higher in robustness for the posture change of the placed finger, the recognition performance is higher, the effectiveness of the method is fully explained, and the application performance of the finger vein recognition technology in the real environment is further improved.

Description

technical field [0001] The invention belongs to the fields of biological feature recognition and computer vision, and in particular relates to a finger vein recognition method based on fusion of local and global feature networks. Background technique [0002] Finger vein recognition is an emerging biometric technology. Due to its characteristics that are difficult to replicate inside the finger, high security and rapid recognition, it is more and more widely used in security fields such as medical care, military industry, education, and finance. . In the process of actual use, in order to consider the user experience, the finger vein image acquisition device does not strictly fix the user's finger, and the user will inevitably have posture changes such as translation and rotation when placing the finger, resulting in the difference between the collected similar finger vein images Relatively large, which reduces the similarity of extracted similar finger vein features, affec...

Images