一种有效的指纹图像预处理方法  

An Effective Method of Fingerprint Image Preprocessing

作　　者：孙林森[1] 吴小培[1] 项明[1] 

机构地区：[1]安徽大学计算机智能与信息处理教育部重点实验室,安徽合肥230039

出　　处：《计算机技术与发展》2009年第2期133-136,共4页Computer Technology and Development

基　　金：国家自然科学基金资助项目(60375010)

摘　　要：预处理是指纹自动识别系统中非常关键的部分,它直接影响着指纹识别的最终效果。指纹预处理一般包括规格化、方向图计算、脊线频率计算、增强、二值化、细化等环节。文中研究并实现了一种有效的指纹图像预处理方法,并采用了一种高效的指纹细化算法。实验结果表明,这种方法能有效地去除传感器表面残留纹印引入的噪声,进一步增强了指纹的脊线和谷线,使指纹纹线变得清晰、连续、光滑,改善指纹图像的质量,提高了指纹识别的可靠性。Preprocessing plays a key role in the fingerprim identification system, which directly influences the final accuracy of fingerprint identification.The preprocessing in the automatic fingerprint identification system usually includes six steps： normalization, directional graph computation, ridgeline frequency computation,enhancement, binarization and thinning. An effective method of fingerprint image preprocessing is accomplished and a resultful thinning algorithm is adopted in this paper. Experiment results show that this kind of algorithm can availably wipe off yawp imported by the incomplete leave fingerprint- masking of sensor surface, and also further enhance ridge line and vale line of fingerprint so that make the lines of fingerprint clesr,continuum and lubricity,at the same time, effectively improves the quality of fingerprint images and promotes the reliability of fingerprint identification.

关 键 词：指纹 预处理 增强 细化 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]