基于Gabor小波和LLE的掌纹识别

›› 2015, Vol. 28 ›› Issue (7): 145-.

基于Gabor小波和LLE的掌纹识别

夏德群,陈玮

(上海理工大学光电信息与计算机工程学院,上海 200093)

出版日期:2015-07-15 发布日期:2015-07-13
作者简介:陈玮(1964—),女,副教授。研究方向:计算机控制技术,模式识别,机器视觉。E-mail:chenw1964@126.com。夏德群(1989—),男,硕士研究生。研究方向:模式识别,图像处理,机器视觉。
基金资助:
沪江基金资助项目(C14002)

Palmprint Recognition Based on Gabor Wavelets and LLE

XIA Dequn,CHEN Wei

(School of Optical-Electrical and Computer Engineering,University of Shanghai for Science and Technology,Shanghai 200093,China)

Online:2015-07-15 Published:2015-07-13

摘要/Abstract

摘要：

为了更好地提取掌纹图像的非线性特征,文中提出一种基于Gabor小波变换和局部线性嵌入的掌纹识别算法。通过提取ROI进行光照和滤波预处理,之后进行Gabor小波变换,提取掌纹图像的多尺度特征,利用非线性的LLE算法提取主元,用最近邻方法进行分类。通过PolyU掌纹库进行验证,比较了预处理、不同ROI提取方法、LLE算法的参数对识别率的影响。实验表明,此方法相比于传统的线性降维算法以及单独的LLE算法在识别率上均有所提高。

关键词: 多尺度特征, 部线性嵌入, 非线性降维, 掌纹识别

Abstract:

An algorithm based on Gabor wavelet transform and palmprint recognition locally linear embedding (LLE) is proposed for better extraction of non-linear characteristics.Firstly,region of interest is extracted and preprocessed through filtering and suppression light.Then,the multi-scale characteristics of the palmprint image are obtained by wavelet transform of Gabor and the principal component is extracted by the non-linear LLE algorithm.Finally the nearest neighbor classifier is used to classify the palmprint.The experiment is based on the PolyU palmprint database and compares the effects on recognition rate of the preprocessing,different ROI extraction methods,and the parameters of the LLE algorithm.The experimental results show that this method achieves better recognition rate than both the traditional linear dimension reduction algorithm and the separate LLE algorithm.

Key words: multi scale characteristics;locally linear embedding;nonlinear dimension reduction;palmprint recognition

中图分类号:

TP391.41

夏德群,陈玮. 基于Gabor小波和LLE的掌纹识别[J]. , 2015, 28(7): 145-.

XIA Dequn,CHEN Wei. Palmprint Recognition Based on Gabor Wavelets and LLE[J]. , 2015, 28(7): 145-.