Multimodal biometric identification system based on finger geometry, knuckle print and palm print
Multimodal biometric identification system based on finger geometry, knuckle print and palm print
复制标题
DOI：
10.1016/j.patrec.2010.05.010
复制
发表时间：
2010-09
期刊：
影响因子：
--
通讯作者：
Leqing Zhu;S. Zhang
中科院分区：
文献类型：
--
作者：
Leqing Zhu;S. Zhang
提出了一种基于手指几何特征、指关节纹特征和掌纹特征的多通道生物特征识别系统。首先对数码相机采集的手部图像进行预处理，得到手指感兴趣区域和手掌感兴趣区域。从手指ROI中提取食指、中指、无名指和小指的手指几何特征和指关节纹特征;从手掌ROI中提取用关键点表示的掌纹特征及其局部描述子。采用由粗到精的分层方法匹配多个特征，在大数据库中实现高效的手部识别。采用决策层与规则融合的方法，改进了组合方案。实验结果证明了该方法的可行性和有效性。
This paper presents a multimodal biometric identification system based on finger geometry, knuckle print and palm print features of the human hand. The hand image captured from digital camera was first preprocessed to get the finger ROI (Region Of Interest) and palm ROI. Finger geometry features and knuckle print features of index, middle, ring and little fingers were extracted from the finger ROI; palm print features represented with keypoints and their local descriptors were extracted from palm ROI. A coarse-to-fine hierarchical method was employed to match multiple features for efficient hand recognition in a large database. The decision level AND rule fusion was adopted which has shown the improvement of the combined scheme. Our experimental results demonstrate the feasibility and effectiveness of the proposed method.