基于Gaussian-Hermite矩和改进的Poincare Index的指纹奇异点提取

在指纹分类和匹配中,准确、可靠地提取奇异点十分重要.针对低质量指纹图像奇异点检测中精确定位和可靠性判断这一难题,提出了一种两阶段的奇异点提取算法.首先,针对现有Poincare index方法存在伪点检出较多和抗噪性较弱的问题,通过对其改进实现候选奇异点位置的确定;然后,再通过计算候选奇异点周围圆形邻域的Gaussian-Hermite矩分布属性值来判断其真伪.方法有效结合了奇异点周围邻域的纹线方向和纹线一致性信息,能够从指纹图像中较为准确、可靠地检测出奇异点.在NIST-4和南京大学活体指纹库上的实验结果验证了该方法的有效性和鲁棒性.在从NIST-4中随机抽取的500幅指纹图像上,奇异点的检测准确率为93.05%(Core点准确率为96.93%,Delta点准确率为86.43%).

Singular Point Extraction from Fingerprint Based on Gaussian-Hermite Moment and Improved Poincare Index

It is very important to extract singular points accurately and reliably for classification and matching of fingerprints. To deal with the difficulty in extracting singular points from fingerprint image of low quality, a two-phase algorithm for singular points extraction is presented in this paper. In the first phase, to heighten anti-noise capability of traditional Poincare index and reduce false singularities, an improved algorithm for Poincare index is proposed, and then it is used to extract candidate si...