Feature Extraction of Finger-Vein Patterns
| Autor: | Chao-Yu Yang, 楊兆佑 |
|---|---|
| Rok vydání: | 2015 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 103 Biometrics recognition is very popular in recent years, that use humans face、iris、voice、fingerprint to recognize, and the biometrics recognition mainstream become vein recognition. Due to the uniqueness of the finger-vein, and others will not have the same finger vein image. And has physiological characteristics of a living body, it can’t easily be copied to theft of personal identity. And its acquisition is not very difficult. This is where the advantages of finger vein. In this paper, we use of curvature to determine whether is the vein feature. The first, we make the image processing in database, and then using the maximum curvature to find the curvature of the point. We use vein into the valley to find the vein pattern of distribution.When the false accept rate is 1.0037%, the genuine accept rate is 100%. Experimental results show that this method can effectively identify research vein area, and be able to compare the results. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|