一种利用稀有细节改善匹配器的指纹自动识别方法

A Method Automatically Recogniting Fingerprint through Improving Matcher with Some Rare Details

为了提高自动指纹识别系统(AFIS)处理隐约指纹的效率和准确度,本文提出使用稀有细节改善匹配器进行隐约指纹的自动识别的方法。首先,以稀有细节特征作为参考点,基于隐约指纹与十指指纹样本的细节点之间的最小二乘计算相似度得分,然后,根据上一阶段的拟合误差,对基于细节的匹配器的相似度得分进行修正。最后,根据隐约指纹和十指指纹样本的细节特征集合之间的仿射变换的最小二乘拟合,对匹配或不匹配情况自动判定。结果表明,与基于稀有细节特征的算法相结合后,三种特征匹配器的识别准确度均得到了显著提升。

In order to improve the efficiency and accuracy of automatic fingerprint identification system(AFIS)in dealing with hidden fingerprints,rare details is used to improve the matcher and it is carried out automatic identification of hidden fingerprints.Firstly,the similarity score is calculated based on the least squares between the minutiae of the implicit fingerprint and the ten fingerprint samples,and then the similarity score of the minutiae-based matcher is corrected according to the fitting error of the previous stage.Finally,the matching or mismatching can be automatically determined according to the least square fitting of affine transformation between the implicit fingerprint and ten fingerprint samples.The experimental results show that the recognition accuracy of the three feature matchers has been significantly improved by combining with the algorithm based on rare detail features.