灰度共生矩阵在指纹图像分割中的应用-数据采集与处理.doc

——————————— 基金项目：河南省高等学校青年骨干教师资助计划（2009GGJS-120） 收稿日期： 灰度共生矩阵在指纹图像分割中的应用 李慧娜1，郭超峰1，平源1,2 （1.许昌学院，计算机科学与技术学院，河南许昌 461000；2.北京邮电大学，计算机学院，北京 100876） 摘 要：指纹图像分割是自动指纹识别系统的关键步骤之一。通过分析指纹图像的灰度级数、位移量及相对方向与其灰度共生矩阵的二次统计特征之间的关系，提出了一种基于灰度共生矩阵的指纹图像分割算法。该算法先将指纹图像分割成矩形块，得到每个矩形块在不同相对方向上的灰度共生矩阵的对比度，然后将其对比度方差与预设阈值进行比较，完成前景或背景区的快速判断。分析和实验表明，该算法分割指纹效果较好，并且对不同的采集环境和图像质量都体现出较强的健壮性。 关键词：指纹图像分割；纹理特征；灰度共生矩阵；二次统计特征；对比度方差 中图分类号：TP391 文献标志码：A The Application of Gray Level Co-occurrence Matrix for Fingerprint Segmentation LI Hui-na1，GUO Chao-feng1，PING Yuan1,2 （1. Department of Computer Science and Technology, Xuchang University, Xuchang, Henan 461000, China； 2. Department of Computer Science, Beijing University of Posts and Telecommunications, Beijing 100876, China） Abstract: Fingerprint segmentation has been considered as one of the critical processes of the automatic fingerprint identification system. Following the analysis of the relationship between the second order statistical characteristics and the grey-scale level, the offset value and the relative direction, an innovative fingerprint segmentation algorithm based on the gray level co-occurrence matrix (GLCM) is thus presented. Firstly, the fingerprint is split into a number of rectangular blocks to get the contrasts of GLCM for each in different directions. And then, to judge for whether a rectangular block is the prospect region or not, the proposed algorithm compares its variance of the contrast with the predefined threshold. The theoretical analysis and experiment results on the FVC2004 show that the proposed algorithm performs well and is robust in handling the varied qualities of fingerprint images collected in any circumstance. Key words: fingerprint segmentation;textural features; gray level co-occurrence matrix; second order statistical characteristics ; contrast variance 1 引言 指纹识别是目前应用最广泛的生物特征识别技术之一。自动指纹识别系统（Automatic fingerprint identification System, AFIS）一般由指纹采集、指纹预处理、特征提取、指纹分类、指纹匹配等几部分组成。指纹分割属于指纹预处理，分割结果可以使自动指纹