摘要
针对手形特点和现有的手形认证方法的不足,提出了一种新颖的基于有序手形轮廓点匹配的手形验证方法。摆脱了固定栓的束缚,运算量小。系统首先对预处理后的手形图像进行边界跟踪后提取手指的关键特征点分离手指,运用对有序边缘点进行运算的手指归一化算法进行图像标准化,最后,运用新型点匹配算法进行自动鉴别。通过小样本实验检测,该方法在鲁棒性、准确率、和运算量方面具有良好的综合性能。
According to the hand shape characteristics and the insufficient of the existing hand shape attestation methods, this paper proposes a new confirmation method which is based on the ordered hand shape contour to match by the points. Getting rid of the fetter of fixed hitch, and having small operands. In this method, the system lines out the fingers＇ characteristic points to separation the figures after carrying on boundary track of the pretreatment picture ,then it uses figure normalization algorithm to the ordered boundary points. At last, the system can carry on the automatic distinction using the new points matching method. Through the small sample experiment, we can see this method has a good overall performance in robustness, accuracy and operand.
出处
《计算机安全》
2009年第1期73-76,共4页
Network & Computer Security
基金
浙江省新苗人才计划项目(2007G60G2070040)资助
