Finger vein recognition method and system based on minutiae area matching

Abstract

The present disclosure provides a finger vein recognition method and system based on minutiae region matching. Among them, the finger vein recognition method based on minutiae region matching includes preprocessing the finger vein image to obtain a region of interest with normalized size and gray scale; dividing the region of interest into several region blocks, and according to each region block The eigenvalues ​​of the Hessian matrix of the corresponding minutiae are used to determine the position of the corresponding minutiae, and the minutiae feature descriptor is assigned; using the assigned minutiae feature descriptor, a pair of minutiae points in the two finger vein images are selected to match the two finger vein images For all the minutiae points in a certain neighborhood corresponding to the pair of minutiae points, if the number of pairs of minutiae points that are successfully matched is the largest, then the pair of minutiae points selected in the two finger vein images are matched successfully; The ratio of the logarithm of minutiae points and the number of regional blocks is used as the matching score. If the matching score is the largest, it is determined that the current two finger vein images are successfully matched.

Description

technical field [0001] The present disclosure belongs to the field of finger vein recognition in biological feature recognition, and in particular relates to a finger vein recognition method and system based on minutiae region matching. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Finger vein recognition has been widely recognized by researchers at home and abroad for its unique advantages: (1) It is not easy to be copied. Finger vein recognition is a living body recognition, and the image used is obtained by irradiating the blood flow of finger veins with near-infrared light, so it is difficult to be forged and copied. (2) Security. Finger veins are hidden inside the human body, invisible to the human eye, and will not be stolen or embezzled. (3) Convenience. Doing things with hands is a human habit, and using fingers for identity...

AI Technical Summary

Problems solved by technology

[0006] (a) Affected by image quality, etc., the feature points extracted in finger vein images are often not rich enough, which affects the performance of recognition;

[0007] (b) During the matching process of two images, a feature point needs to be matched with all the feature points in the other image, and then the point with the highest matching score is selected as the best matching point. In the matching process, no The location information of the feature points has too much redundant matching, and it is easy to cause false matching under the condition that the feature points are not distinguishable enough

Images