Abstract: It is very important to locate core point accurately and reliably for classification and matching of fingerprints. This paper presents a novel hybrid method based on modified orientation field estimation and improved complex filtering technique to solve the problem of traditional orientation field algorithm. The experiment results show that the proposed algorithm is effective and robust.

Key words: fingerprint, core point localization, orientation field, complex filter

摘要： 准确、可靠地定位指纹核心点对指纹的分类和匹配具有重要意义。该文分析了一种传统的基于方向场特征的核心点定位算法，并针对传统算法不能准确定位的局限性，提出了一种新的复合指纹核心点定位算法，将改进的方向场估计法和多级滤波器技术相结合，实现核心点的准确定位。实验结果表明，该算法能有效实现指纹核心点的定位，并具有较好的鲁棒性。

关键词: 指纹, 核心点定位, 方向场, 多级滤波器

CLC Number: 

• TP301.6