光学学报, 2009, 29 (3): 643, 网络出版: 2009-03-17
基于非负矩阵分解和广义判别分析的掌纹识别
Palmprint Recognition Based on Non-Negative Matrix Factorization and General Discriminant Analysis
生物特征识别 特征提取 非负矩阵分解 广义判别分析 biometrics recognition feature extraction non-negative matrix factorization general discriminant analysis
摘要
非负矩阵分解(NMF)具有非负性和局部性的特点,是一种新型的特征提取方法。由于NMF是非监督学习算法,运用NMF提取掌纹特征时没有考虑训练样本的类别信息,因而分类效果不够理想。为了在提取掌纹特征的同时融入类别信息,提出运用非负矩阵分解和广义判别分析(GDA)相结合的方法进行掌纹识别。为了降低计算的复杂性,在特征提取之前,应用小波变换对掌纹图像进行三级分解,提取低频子图像。在低频子图像上应用NMF+GDA提取掌纹特征,计算特征向量间的余弦距离进行掌纹匹配。运用PolyU掌纹图像库进行测试,结果表明,与主元分析(PCA)、独立元分析(ICA)和NMF相比,算法的等误率(EER)最低为0.16%,特征提取和匹配总时间为0.812 s,满足实时系统的要求。
Abstract
Non-negative matrix factorization (NMF) has non-negative and local characteristics, and it is a new feature extraction method. NMF is an unsupervised learning method, and does not consider class information of samples applied to extract palmprint features, so the classification effect is not ideal. In order to fuse class information when the features of images are extracted, a palmprint recognition method based on non-negative matrix factorization and general discriminant analysis (GDA) is proposed. Before extracting features, the three-level wavelet transform is utilized to palmprint images to get the low-frequency sub-images. Then NMF and GDA are applied to extract palmprint features. The cosine distance between two feature vectors is calculated to match palmprint. The new algorithm is tested in PolyU plmprint database. The results show that compared with principal component analysis (PCA), independent component analysis (ICA) and NMF, the equal error rate (EER) of the new algorithm is the lowest as 0.16%, and the total time for feature extraction and matching is 0.812 s, so it meets the real-time system specification.
郭金玉, 苑玮琦. 基于非负矩阵分解和广义判别分析的掌纹识别[J]. 光学学报, 2009, 29(3): 643. Guo Jinyu, Yuan Weiqi. Palmprint Recognition Based on Non-Negative Matrix Factorization and General Discriminant Analysis[J]. Acta Optica Sinica, 2009, 29(3): 643.