光电工程, 2011, 38 (10): 110, 网络出版: 2011-10-21
分块 Radon变换在低对比度掌纹特征提取中的应用
Application of Block Radon Transform to Feature Extraction of Low Contrast Palmprint
生物特征识别 掌纹识别 特征提取 小波变换 分块 Radon变换 biometrics recognition palmprint recognition feature extraction wavelet transform block Radon transform
摘要
特征提取是低对比度掌纹识别的关键步骤。针对掌纹纹理特征明显的特点,本文提出了一种分块 Radon变换的掌纹特征提取方法。该方法先对掌纹感兴趣区域进行一级小波分解去噪降维,接着对低频子图像进行分块以圈定局部主要纹理,最后把所有分块后的子图像进行 70°~140° Radon变换,所获得的线积分组合在一起构成该图像的特征向量。运用 UST掌纹图像库,对本文算法进行了测试。从识别率达到 94%的实验结果看,此方法能够满足对采集图像无过多要求的认证系统的使用。
Abstract
Feature extraction is a critical step for low contrast palmprint recognition. According to the characteristics with obvious palmprint texture features, a block Radon transform method is presented for palmprint feature extraction. Firstly, the method denoises region of interest of the palmprint and reduces dimension with the first-level wavelet decomposition. Then it blocks the low-frequency sub-image to delineate local primary textures. At last, after all the sub-block images are transformed during 70°~140° by Radon transform method, the line integrals obtained constitute feature vector for the image. The method was tested on the basis of UST palmprint image database. From the experimental results of 94% recognition rate, the method can satisfy the application for authentication systems without excessive demands for collection images.
刘玉芹, 苑玮琦, 郭金玉. 分块 Radon变换在低对比度掌纹特征提取中的应用[J]. 光电工程, 2011, 38(10): 110. LIU Yu-qin, YUAN Wei-qi, GUO Jin-yu. Application of Block Radon Transform to Feature Extraction of Low Contrast Palmprint[J]. Opto-Electronic Engineering, 2011, 38(10): 110.