摘要
为了解决掌纹特征提取过程中,手掌的非平面问题导致的伪主线噪音信息并简化运算,对重构的掌纹图像进行了局部离散余弦变换.解决了重构后图像噪音敏感性问题,有效地区分了掌纹主线、掌纹褶纹和乳突纹.由二维主元分析算法获得较稳健的识别特征.通过香港理工大学公布的PolyU掌纹数据库的实验,同二维主元分析算法相比,小波重构与局部离散余弦变换的2DPCA掌纹识别算法正确识别率较高,识别效率较高.
In order to solve the problem that the palm-print image quality is influenced by the arch of the palm-print,which caused platn-print recognition tare to descend, the noise from reconstructed image was local DCT eliminated. The palm-print principle-line, plicate-line and papilla-line were distinguished efficiently. And 2DPCA obtained robust recognition features. Experimental results on HongKong PolyU palm-print experiments show that by the method reeogrintion tate and recognition efficiency is higher than that by 2DPCA.
出处
《光子学报》
EI
CAS
CSCD
北大核心
2009年第6期1566-1571,共6页
Acta Photonica Sinica
基金
国家自然科学基金(60573056)
浙江省自然科学基金(Z106335,Y107759,Y107293)
浙江省科技计划项目(2008C21G2200007)
广东省自然科学基金(07010869,032356)
湖州市自然科学资金(2006YZ03)资助
关键词
掌纹识别
提升小波重构
局部离散余弦变换
二维主元分析
Paim-print recognition
Lifting wavelet reconstruction
Local discrete cosine transform
Two- dimensional principle component analysis
