Finger vein line restoration method based on gray scale neighbor and variance constraint
A technology of finger veins and repair methods, which is applied in character and pattern recognition, instruments, computer parts, etc., and can solve problems such as broken branches of vein lines
Patent Information
- Authority / Receiving Office
- CN · China
- Current Assignee / Owner
- Publication Date
- 2014-05-07
- Estimated Expiration
- Not applicable · inactive patent
Smart Images
Figure 1 Figure 2 Figure 3
Abstract
Description
technical field
[0001] The invention mainly relates to a method for repairing finger vein lines based on gray-scale neighbors and variance constraints, and belongs to the technical field of security biological feature recognition. Background technique
[0002] Finger vein recognition technology is currently a research hotspot in the field of biometric identification. Its main advantage is that the veins are hidden inside the finger, which is not easy to be forged and stolen, and is safe and reliable. The point pattern matching method is one of the commonly used methods in the field of finger vein recognition. This method is based on the extracted features of the thinned finger vein pattern image for matching.
[0003] The imaging mechanism of finger veins leads to low quality of collected finger vein images, which brings great difficulties to obtain clear and complete vein patterns. In order to obtain clear and complete vein patterns, many meaningful algorithms have been pr...
Examples
Embodiment Construction
[0059] A finger vein texture repair method based on gray-scale neighbors and variance constraints. First, the MRLT method, mathematical morphology top-hat transformation, and mathematical morphology hit and miss transformation are used to obtain the refined finger vein texture; Then locate the initial position of the vein pattern break, and determine the candidate target point set according to the direction of the vein pattern; then propose the gray-scale neighbor criterion to select suspicious target points from the candidate target point set; finally propose the intra-class variance upper limit consistency criterion and Boundary constraints, to determine whether the suspicious target point is a lost target point, and iteratively search for the lost target point, and repair the broken vein pattern.
[0060] The specific content is:
[0061] 1. Finger vein texture extraction
[0062] Finger vein texture extraction includes three steps of image segmentation, image filtering an...