多重分形在掌纹识别中的研究  

A multifractal approach to palmprint recognition

作　　者：李彤[1] 商朋见[1] 

机构地区：[1]北京交通大学理学院,北京100044

出　　处：《物理学报》2007年第8期4393-4400,共8页Acta Physica Sinica

基　　金：国家重点基础研究发展规划(批准号:2004CB318005)资助的课题.~~

摘　　要：通过对掌纹的概率密度分布和配分函数的分析,得到掌纹分布具有一定的多重分形性.进一步求取掌纹多重分形谱的宽度、极大值以及谱曲线的不对称程度,并提出以这些参数作为掌纹识别的特征量.这可能为多重分形理论在生物特征识别领域中的应用带来新的思路与方法.The purpose of the present study is to investigate the presence of multifractal behaviors of the palmprint. By studying the probability distribution and the partition function, we show that the palmprints possess multifractal characteristics. The width spread, the maximum of multifractal spectrum, and a parameter which describes the asymmetry of the spectrum are proposed as the distinguishing palmprint features. This may provide some factors of importance for palmprint recognition, and shed some light on the problem of biometric recognition.

关 键 词：分形 模式识别 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]