一种新的指纹图像分割算法

摘要/Abstract

摘要：

指纹图像分割是自动指纹识别的重要步骤。对指纹特征和传统指纹分割方法进行了研究，提出了一种新的指纹图像分割算法。先对指纹图像进行裁剪，如果指纹图像对比度较低，则对图像进行均衡化处理；然后对图像进行顶帽变换，补偿不均匀的背景亮度；最后用迭代自组织分析算法(ISODATA聚类)对图像进行分块分割和形态学图像处理。对国际指纹识别竞赛(FVC)数据库不同质量的指纹进行了测试，实验结果表明，此算法对不同质量的指纹是有效的，效果好于传统指纹分割方法。

关键词: 分割, 指纹, 算法, ISODATA聚类, 形态学图像处理

Abstract:

Fingerprint segmentation is an important step of automatic fingerprint identification system. The features of the fingerprint and the tradition fingerprint segmentation algorithms are studied. A new algorithm of fingerprint segmentation is proposed. Firstly, the print area is found quickly and the image is cropped. If the contrast is low, the histogram equalization is applied on the image. Then tophat transform is used on the image to compensate the nonuniform background intensity. After that, the algorithm of the iterative selforganizing data analysis technique is applied and the image is segmented by block. And the morphological image processing is adopted. The algorithm is tested on the different quality fingerprints of the FVC (Fingerprint Verification Competition) fingerprint databases. The experimental results indicate that the proposed algorithm is effective for different quality fingerprints and outperforms the tradition fingerprint segmentation algorithms.

Key words: segmentation;fingerprint;algorithm;ISODATA clustering;morphological processing

刘汉英1，周剑勋2. 一种新的指纹图像分割算法[J]. J4, 2014, 36(06): 1137-1147.

LIU Hanying1,ZHOU Jianxun2. A novel algorithm for fingerprint segmentation [J]. J4, 2014, 36(06): 1137-1147.

参考文献

［1］Zhu En,Yin Jianping,Hu Chunfeng,et al.Systematic methods of fingerprint fidge orientation estimation and image segmentation［J］. Journal of Tongji University (Natural Science), 2007, 35(5):669674. (in Chinese)
［2］Mehtre B M,Chatterjee B.Segmentation of fingerprint imagesA composite method［J］.Pattern Recognition,1989,22(4):381385.
［3］Wang Feng.Fingerprint image quality assessment and preprocessing［D］. Nanjing:Nanjing University of Aeronautics and Astronautics,2008. (in Chinese)
［4］Chen Xinjian, Tian Jie, Cheng Jiangang, et al. Segmentation of fingerprint images using linear classifier［J］.EURASIP Journal on Applied Signal Processing,2004(4):480494.
［5］Yang Gongping,Chen Yawei,Yin Yilong,et al.A method of fingerprint segmentation base on transductive learning［P］.Chinese Patent:201010202767.4,2010.(in Chinese)
［6］Guo Fangfei. The fingerprint quality evaluation and its application［D］. Xi’an:Xidian University,2010.(in Chinese)
［7］Chen Xiaoguang,Feng Jufu.Segmentation of fingerprint images using discriminant analysis of multiple features［J］. Acta Scientiarum Naturalium Universitatis Pekinensis, 2009,45(4):579584.(in Chinese)
［8］Mehtre B M, Murthy N N, Kapoor S, et al. Segmentation of fingerprint images using the directional image［J］.Pattern Recognition,1987,20(4):429435.
［9］Zhang Lixiang.Research on the fingerprint image preprocessing［D］. Changsha:Central South University, 2010.(in Chinese)
［10］Zhou Yongdong. Design of fingerprint image enhancement algorithm and accelerator［D］.Hangzhou:Zhejiang University,2006.(in Chinese)
［11］Deng Liang, Zhang Xinman, Shen Honghui, et al. A universal fingerprint segmentation algorithm based on linear classifier［J］.Microelectronics & Computer,2011,28(12):124128.(in Chinese)
［12］Mei Yuan, Cao Guo, Sun Huaijiang, et al. Effective method for the segmentation of fingerprint images based on new feature［J］.Computer Science,2009,36(11):273278.(in Chinese)
［13］Wu Xianli, Jiang Changhong. Research of segmentation algorithm of fingerprint image［J］. Journal of Shenyang Institute of Chemical Technology, 2005, 19(1):4749.(in Chinese)
［14］Zhu En, Yin Jianping, Hu Chunfeng, et al. A systematic method for fingerprint ridge orientation estimation and image segmentation［J］. Pattern Recognition, 2006,39(8):14521472.
［15］Wang Feng. Application research of DS evidence theory in fingerprint image segmentation［J］. Computer Engineering and Applications, 2010, 46(24):169172. (in Chinese)
［16］Tang Liangrui, Xie Xiaohui, Cai Anni, et al. Fingerprint image segmentation based on DS evidence theory［J］.Chinese Journal of Computers,2003,26(7):887892.(in Chinese)
［17］Zhang Hongwei,Shi Zhichen.Fingerprint segmentation base on kmean clustering and linear neighborhood spread［P］. Chinese Patent:201110187105.9,2011.(in Chinese)
［18］Zhu Xinzhong,Zhao Jianmin,Zhu En, et al. A method of fingerprint segmentation and fingerprint ridge orientation estimation based on BP neural network［P］. Chinese Patent:200710164536.7,2007.(in Chinese)
［19］Rafael C G, Richard E W, Steven L E. Digital image processing using MATLAB［M］. Beijing:Publishing House of Electronics Industry,2009.
［20］Davide M, Dario M, Anil K J, et al. Handbook of fingerprint recognition［M］. 2nd ed. London:Springer,2009.
［21］Guo Wenqiang, Hou Yongyan. Digital image processing［M］.Xi’an:Xidian University Publishing House,2009.(in Chinese)
［22］Nalini K R,Sharat C,Jonathan H C,et al. Generating cancelable fingerprint templates［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007,29(4):561572.
［23］Zhang Shi, Dong Jianwei, She Lihuang. The methodology of evaluating segmentation algorithms on medical image［J］. Journal of Image and Graphics, 2009,14(9):18721880.(in Chinese)
附中文参考文献：
［1］祝恩,殷建平,胡春风,等.指纹纹路方向计算与图像分割的系统方法［J］. 同济大学学报(自然科学版),2007,35(5):669674.
［3］王峰.指纹图像质量评估与预处理［D］.南京:南京航空航天大学,2008.
［5］杨公平,陈亚伟,尹义龙,等. 一种基于直推式学习的指纹图像分割方法［P］.中国专利:201010202767.4,2010.
［6］郭芳菲. 指纹图像质量分析及其应用研究［D］. 西安:西安电子科技大学,2010.
［7］陈小光,封举富.基于多特征判别分析的指纹图像分割方法［J］.北京大学学报(自然科学版),2009,45(4):579584.
［9］张理想. 指纹图像预处理研究［D］. 长沙:中南大学,2010.
［10］周永东. 指纹图像增强算法研究和加速器设计［D］.杭州:浙江大学,2006.
［11］邓亮,张新曼,沈虹晖,等. 一种基于线性分类器的通用指纹分割方法［J］. 微电子学与计算机,2011,28(12):124128.
［12］梅园,曹国,孙怀江,等. 一种基于新特征的有效指纹图像分割算法［J］. 计算机科学,2009,36(11):273278.
［13］吴显丽,姜长洪. 指纹图像的分层分割算法［J］. 沈阳化工学院学报,2005,19(1):4749.
［15］王峰. DS证据理论在指纹图像分割中的应用研究［J］. 计算机工程与应用,2010,46(24):169172.
［16］唐良瑞,谢晓辉,蔡安妮,等.基于DS证据理论的指纹图像分割方法［J］.计算机学报,2003,26(7):887892.
［17］张宏伟,史智臣. 基于k均值聚类与线性邻域传播结合的指纹图像分割方法［P］.中国专利：201110187105.9,2011.
［18］朱信忠,赵建民,祝恩,等. 一种基于BP神经网络的指纹图像纹路方向计算和图像分割方法［P］.中国专利:200710164536.7,2007.
［21］郭文强,侯勇严.数字图像处理［M］.西安:西安电子科技大学出版社,2009.
［23］张石,董建威,佘黎煌.医学图像分割算法的评价方法［J］.中国图象图形学报,2009,14(9):18721880.

[1]	闫盼，谭瑛，张建华. 一种用于进化算法历史计算数据的高效利用方法[J]. J4, 20160101, 38(01): 62-66.
[2]	余子丞, 凌捷. 基于Transformer和多特征融合的DGA域名检测方法[J]. 计算机工程与科学, 2023, 45(08): 1416-1423.
[3]	侯占伟, 李鑫, 王辉, 申自浩, 刘琨, 刘沛骞. 面向路网的空间众包隐私保护任务分配算法[J]. 计算机工程与科学, 2023, 45(08): 1424-1432.
[4]	罗仕杭, 何庆. 多策略融合改进的均衡优化算法及其应用[J]. 计算机工程与科学, 2023, 45(08): 1508-1520.
[5]	付祥, 黎梓浩, 黄子潇, 杨曜嘉, 刘定东, 张春晖, 李小芳. 符号化量子计算模拟器SymQC[J]. 计算机工程与科学, 2023, 45(07): 1159-1169.
[6]	张一楠, 丁建完. 基于WLS-MBO算法的串联机器人动力学参数辨识[J]. 计算机工程与科学, 2023, 45(07): 1274-1281.
[7]	柴岩, 朱玉, 任生. 多策略协同的改进鲸鱼优化算法[J]. 计算机工程与科学, 2023, 45(07): 1308-1319.
[8]	黄学雨, 罗华. 融合正余弦策略的算术优化算法[J]. 计算机工程与科学, 2023, 45(07): 1320-1330.
[9]	赖明澈, 吕方旭, 张庚, 许超龙. 面向112 Gbps PAM4串行接收机的低误码协同自适应均衡器[J]. 计算机工程与科学, 2023, 45(06): 951-960.
[10]	史明川, 邹鸿基, 秦志楷, 李暾. 基于WCOJ的UPF供电状态分析器的设计与实现[J]. 计算机工程与科学, 2023, 45(06): 979-986.
[11]	黄学雨, 罗华. 自适应变异蝴蝶优化算法[J]. 计算机工程与科学, 2023, 45(06): 1123-1133.
[12]	唐宇, 代琪, 杨志伟, 杨爱民, 陈丽芳, . 基于优化随机森林的软件缺陷预测算法研究[J]. 计算机工程与科学, 2023, 45(05): 830-839.
[13]	于家斌, 陈志豪, 邓维, 许继平, 赵峙尧, 王小艺. 一种无人巡航船遍历多目标点的路径规划算法研究[J]. 计算机工程与科学, 2023, 45(05): 840-848.
[14]	霍爱清, 张书涵, 杨玉艳, 胥静蓉, 王泽文. 密集交通场景中改进YOLOv3目标检测优化算法[J]. 计算机工程与科学, 2023, 45(05): 878-884.
[15]	付接递, 李振东, 郭辉. 基于教与学和逐维柯西变异的鲸鱼优化算法[J]. 计算机工程与科学, 2023, 45(05): 940-950.