机构地区: 华南师范大学
出 处: 《量子电子学报》 2009年第5期518-524,共7页
摘 要: 提出了一种新的基于方向场离散傅里叶变换(Discrete Fourier transform,DFT)和角点检测的指纹奇异点定位算法。对方向场做DFT变换到频域处理能更好地压制噪声。通过角点提取、基于目标标注的聚类方法来定位指纹图像的奇异点。从方向场的极/零点模型出发,导出了若干新颖的性质,说明了奇异点和角点之间的关系。实验结果表明,奇异点定位精度有所提高,处理时间更短。 A new method for locating fingerprint singular points based of orientation field and corner detector is proposed. Orientation field DFT so that noise is better suppressed. Fingerprint singular points on discrete is processed are located Fourier transform (DFT) in frequency domain via by corner detection and clustering based on object labeling. Novel properties, which reveals the relationship between singular points and corners, are derived based on pole/zero model of orientation field. Experimental results show improved accuracy of singular points location and a reduced processing time
关 键 词: 图像处理 指纹图像 离散傅里叶变换 角点检测 奇异点
领 域: [自动化与计算机技术] [自动化与计算机技术]