基于细化图像宏观弧线特征的指纹分类算法

摘要

针对活体指纹采集样本提出了一种新的基于细化图像的指纹分类算法,定义并通过采用脊线追踪算法成功提取了一种反映指纹纹线变化特点和规律的新参量,即宏观弧线特征向量.利用这一新特征对FVC2004库中的指纹进行分类,准确率达98.9%以上,并且对低质量指纹图像具有良好的鲁棒性,消除了传统指纹分类算法过分依赖奇异点的缺陷,具有很强的实用性和一定的推广价值.%This paper provided a new fingerprint classification algorithm based on the thinning image for live fingerprint samples,it for the first time successfully extracted a new parameter suggesting the characteristics and regularity of fingerprint ridges variation by applying the ridge following method,which was defined as macro arc-like eigenvector.The proposed method which using the new eigenvector validated on the FVC2004 database and produced a classification accuracy of 98.9%.Moreover,this classification method also had a good robustness to those fingerprint images of lower quality and eliminated the defect of traditional classification algorithm which depending on the singular point overly.This method has strong application in practice and also some values in popularizing.