【作者】 张虹； 张军； 刘峰；

【Author】 Zhang Hong~1 Zhang Jun~2 Liu Feng~1 (1 Harbin Institute of Technology(Weihai) weihai 264209 China; 2 Adminstration Center for Innovation Fund for Small Technology_bssed Firms beijing 100038 China)

【机构】 哈尔滨工业大学(威海)信息科学与工程学院； 科技型中小企业技术创新基金管理中心；

【摘要】 指纹图像的匹配是指纹识别过程中的一个重要环节。本文提出了一种新的匹配方法,在改进的指纹细化算法基础上进行特征提取和匹配。首先采用两遍扫描串行迭代的细化算法求取指纹的骨架,在骨架上提取特征点,并采用脊线跟踪的方法去除伪特征点,然后采用三角形全等法判断两组特征点是否来自于同一幅指纹图像。实验表明,同常规方法相比,该算法具有很好的匹配效果,尤其对图像质量较差的指纹,具有很好的适应能力。更多还原

【Abstract】 Fingerprint minutiae matching is an important step in fingerprint identification processing.A new fingerprint minutiae matching algorithm was proposed:first a two-pass sequential iterative was used to produce skeleton of finger prints by which the minutiae was extracted and the fake minutiae was deleted,then,a triangle-based fingerprint minutiae matching algorithm was used to decide whether two groups of fingerprint minutia are from the same finger.Experimental results show that the proposed method can match fingerprint images properly,especially low quality fingerprint It has been proved that this algorithm can meet the requirements of fingerprint matching.更多还原