Finger vein indexing method based on multi-scale attention mechanism deep hash

Abstract

The invention provides a finger vein indexing method based on multi-scale attention mechanism deep hash. The method comprises: obtaining a training set including finger vein feature data; traversing and expanding the training set to obtain an expanded training set; extracting finger vein depth features of a multi-scale attention mechanism based on the extended training set and a pre-constructed multi-scale attention feature extraction model; and based on the multi-scale attention mechanism finger vein depth features and a pre-constructed classification supervision model, hash coding model andretrieval task supervision model, performing collaborative training of triple loss functions to generate a final training model. According to the method, a neural network method is mainly adopted, a multi-scale attention mechanism is added, compared with a traditional feature extraction algorithm, the robustness of the features is improved to a certain extent, meanwhile, the model is end-to-end, the integrity of hash coding and feature extraction can be guaranteed, and the coding quality and the coding efficiency are guaranteed.

Description

technical field [0001] The present invention relates to the technical field of finger vein recognition, in particular to a finger vein indexing method based on multi-scale attention mechanism depth hashing. Background technique [0002] In recent years, with the rapid development of biometric identification technology, finger vein recognition technology is gradually known by people. In addition to the inherent characteristics of universality, persistence, uniqueness and collectability, finger vein recognition technology also has the unique attributes of live detection and non-contact characteristics, so it is widely accepted by the public. With the application of finger vein recognition technology becoming more and more widespread, the registered users stored in the database are gradually accumulating, and it is difficult for the past recognition technology to achieve real-time effects under the gradually accumulated data volume. Moreover, traditional manual features are di...

AI Technical Summary

Problems solved by technology

[0004] (1) The model is non-end-to-end, that is, the extraction of finger vein features and hash coding are carried out step by step, and the operating efficiency of the model is difficult to guarantee

[0005] (2) The objective functions of the two modules are not consistent, and the robustness of the hash code generated by the combination of the two modules is difficult to guarantee

Images