Method for extracting region of interest of finger vein based on fusion of finger contour and gradient distribution

Abstract

The invention, which belongs to the field of image processing, proposes a method for extracting a region of interest of a finger vein, thereby providing the reliability guarantee for follow-up fingervein feature extraction and recognition. To be specific, the invention provides a method for extracting a region of interest of a finger vein based on fusion of finger contour and gradient distribution. On the basis of the imaging principle of the finger vein and the characteristic of low absorption coefficient of the near-infrared light by the interphalangeal joint, the finger rotation and gradient distribution are corrected based on the finger contour and the interphalangeal joint position is located; and thus the region of interest having the vein information is extracted automatically. Themethod is mainly applied to the image processing occasion.

Description

technical field [0001] The invention belongs to the field of image processing, in particular to a method for preprocessing finger vein images. Specifically, it relates to a method for extracting a region of interest in finger veins by fusing finger contours and gradient distributions. Background technique [0002] As a new biometric method, finger vein recognition technology has more unique advantages compared with traditional biometric technologies such as fingerprint recognition, palmprint recognition, and face recognition: (1) non-contact; (2) living body detection; (3) high security; (4) portability. Therefore, finger vein recognition technology has wider development space and application prospects. [0003] As the first step in finger vein recognition, ROI (region of interest) extraction of finger vein images plays a vital role in feature extraction and recognition of finger veins. The principle of finger vein imaging is realized by using the absorption characteristi...

AI Technical Summary

Problems solved by technology

[0005] 1. Finger veins are collected in a non-contact manner. Fingers are prone to displacement in the horizontal direction and rotation in the axial direction;

[0006] 2. Affected by uneven illumination, the quality of the collected finger vein images is not high and the contrast is poor;

[0007] 3. Affected by light, finger displacement or rotation, shadow areas are easily generated in finger vein images

[0008] The above-mentioned factors have caused great difficulties in the positioning of the interphalangeal joints, so that the ROI cannot be extracted reliably

Images