手指多模态特征图像姿态同步采集系统设计  

Synchronous acquiring system design of multimodal finger image

作　　者：杨金锋[1] 李常福 YANG Jinfeng;LI Changfu(Intelligent Signal and Image Processing Key Lab of Tianjin,CAUC,Tianjin 300300,China)

机构地区：[1]中国民航大学天津市智能信号与图像处理重点实验室,天津300300

出　　处：《中国民航大学学报》2020年第1期54-59,共6页Journal of Civil Aviation University of China

基　　金：国家自然科学基金项目(61379102,61502498,U1433120);中央高校基本科研业务费专项(3122017001)。

摘　　要：在手指多模态融合识别中,实现指静脉、指节纹和指纹三模态特征图像的姿态统一对提高识别性能十分重要。首先通过采用新的成像模式,在硬件上使手指多模态特征成像姿态趋于统一,然后通过计算手指姿态的方向角度,矫正手指的平面随机转动,在算法上减少手指成像的姿态变化,最后利用成像空间之间的映射关系,实现指静脉和指节纹感兴趣区域(ROI)之间的协调定位。实验结果表明,该手指多模态生物图像采集方案效果稳定,基本解决了手指多模态生物特征采集中存在姿态不一致的问题。In the fusion of multimodal finger identification,pose synchronization of three-modal finger images including finger vein,finger-knuckle-print and finger print is crucial for recognition performance improvement.Firstly,a new hardware imaging mode is adopted to make consistent imaging pose of multimodal finger traits.Secondly,random plane-rotation of finger pose is corrected through finger posture angle calculation to reduce finger imaging posture change using algorithm.Finally,ROI coordination of finger vein and finger-knuckle-print is conducted by image space mapping.Experimental results prove the stable performance of the proposed image acquisition scheme,which basically resolves the finger pose variation.

关 键 词：生物识别 多模态生物特征 姿态同步 系统设计 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]