摘要
掌纹作为一种新的生物特征可用来进行人的身份识别。论文提出了将二维主成分分析方法(2DPCA)应用于掌纹识别的特征提取,并在PolyU掌纹数据库上利用最近邻分类器与余弦距离度量进行了相应的实验,得到了99.4%的正确识别率。二维主成分分析方法相比主成分分析方法(PCA)方法具有更高的识别率和更快的计算速度,尤其是在小样本训练数据的情况下优势更明显。同时论文也研究了不同应用系统下阈值的选取方法。
A palmprint is a relative new biometric feature for personal authentication. A feature extraction method for palmprint recognition based on Two-Dimensional Principal Component Analysis （2DPCA） is proposed in this paper. A series of experiments was performed on the PolyU-Online-Palmprint-Database with a nearest neighbor classifier and cosine distance. The success rate in recognition is 99.14%. The 2DPCA method has higher recognition success rate and is more computationally efficient than PCA, especially for small training samples. The selection of threshold values is also discussed for different application systems.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2008年第9期1929-1933,共5页
Chinese Journal of Scientific Instrument
基金
沈阳工业大学博士启动基金(007114)资助项目
