基于稀疏表示的多模态生物特征识别算法

传统的生物特征识别系统依靠单一来源的生物特征信息完成对象鉴别,但是光照变化、噪声和遮挡等因素对生物特征信息的污染会使其识别性能降低。为此,提出一种多模态稀疏表示算法。在使测试对象不同模态的观测值共享稀疏表示的情况下,用训练数据的稀疏线性组合表示测试数据。算法的优化问题通过一种高效的交替方向方法求解。实验结果表明,该算法的识别性能优于基于信息融合的对比方法。...

Full description

Saved in:
Bibliographic Details
Published in计算机工程 Vol. 42; no. 10; pp. 219 - 225
Main Author 王玉伟 董西伟 陈芸
Format Journal Article
LanguageChinese
Published 九江学院机械与材料工程学院,江西九江,332005%九江学院信息科学与技术学院,江西九江332005 2016
南京邮电大学自动化学院,南京210003%江苏信息职业技术学院物联网工程系,江苏无锡,214153
Subjects
Online AccessGet full text
ISSN1000-3428
DOI10.3969/j.issn.1000-3428.2016.10.038

Cover

More Information
Summary:传统的生物特征识别系统依靠单一来源的生物特征信息完成对象鉴别,但是光照变化、噪声和遮挡等因素对生物特征信息的污染会使其识别性能降低。为此,提出一种多模态稀疏表示算法。在使测试对象不同模态的观测值共享稀疏表示的情况下,用训练数据的稀疏线性组合表示测试数据。算法的优化问题通过一种高效的交替方向方法求解。实验结果表明,该算法的识别性能优于基于信息融合的对比方法。
Bibliography:31-1289/TP
WANG Yuwei1a ,DONG Xiwei1b,2, CHEN Yun3 (1a. School of Mechanical and Materials Engineering; 1b. School of Information Science and Technology, Jiujiang University ,Jiujiang ,Jiangxi 332005 ,China; 2. College of Automation ,Nanjing University of Posts and Telecommunications,Nanjing 210003 ,China; 3.Department of IOT Engineering ,Jiangsu Vocational College of Information Technology ,Wuxi ,Jiangsu 214153 ,China)
Sparse Representation (SR); biometric recognition; information fusion; fingerprint recognition; iris recognition
Traditional biometric recognition system uses single source biometric information for authentication. However, the recognition performance decreases while biometric information is contaminated by various artifacts such as illumination variations,noise, occlusion and so on. A multimodal Sparse Representation (SR) algorithm is proposed, which represents the test data by a sparse linear combination of training data, while enforcing the observations from different modalities of the test su
ISSN:1000-3428
DOI:10.3969/j.issn.1000-3428.2016.10.038