Finger multi-feature comprehensive three-dimensional reconstruction method

Abstract

The invention provides a finger multi-feature comprehensive three-dimensional reconstruction method comprising the following steps: step 1, calibrating a multi-view multi-spectral finger acquisition device; step 2, performing feature matching on the surface texture image of the finger by adopting a multi-view three-dimensional reconstruction algorithm to obtain a sparse three-dimensional point cloud of the surface of the finger and complete multi-view three-dimensional reconstruction; step 3, performing three-dimensional reconstruction on the surface of the finger by adopting a photometric three-dimensional method to obtain dense depth information; step 4, fusing the three-dimensional point cloud subjected to multi-view three-dimensional reconstruction with the dense depth information obtained by the photometric three-dimensional method to obtain a fused three-dimensional Mesh model; and step 5, mapping the surface texture image and the internal vein texture image of the finger to thefused three-dimensional Mesh model to obtain a finger multi-feature comprehensive three-dimensional model. According to the method, the dense three-dimensional model is obtained by fusing multi-view three-dimensional reconstruction and photometric three-dimensional reconstruction so that the situation that the recognition accuracy is reduced due to the three-dimensional modeling method is reduced.

Description

technical field [0001] The invention relates to the technical field of biological feature recognition, and more specifically, relates to a multi-feature comprehensive three-dimensional reconstruction method of fingers. Background technique [0002] Today, when information technology and network technology are highly developed, identification of personal identity and personal information security has become a key social issue that needs to be solved urgently. As a kind of identity authentication and information security technology, biometric identification has been widely used in customs clearance inspection and security monitoring. , financial banking, criminal investigation and household registration management and other fields. Biometric identification technology uses biological characteristics for identification. The biological characteristics used can be mainly divided into physiological characteristics, such as face, fingerprint, iris, finger vein, finger shape, etc.; a...

AI Technical Summary

Problems solved by technology

However, at present, fingerprint sensors and near-infrared cameras are mainly used for feature collection. The two sensors collect corresponding biometric features respectively, which makes the system still have the risk of each biometric feature being counterfeited and attacked separately, and the production cost is relatively high.

At the same time, in actual use of two-dimensional fingerprint and two-dimensional finger vein features, the acquisition area is often inconsistent with the registration template area due to the axial rotation of the finger, which reduces the recognition accuracy.

Images