[1]赵慧敏,李卫军,刘扬阳,等.基于三高斯滤波的低质指纹图像增强方法[J].智能系统学报,2012,7(6):489-493.
　ZHAO Huimin,LI Weijun,LIU Yangyang,et al.A low quality fingerprint image enhancement algorithm based on triGaussian filter[J].CAAI Transactions on Intelligent Systems,2012,7(6):489-493.
点击复制

基于三高斯滤波的低质指纹图像增强方法

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 7 期数: 2012年第6期 页码: 489-493 栏目: 学术论文—机器学习 出版日期: 2012-12-25
Title:
A low quality fingerprint image enhancement algorithm based on triGaussian filter
文章编号:
1673-4785(2012)06-0489-05
作者:
赵慧敏1, 李卫军1, 刘扬阳2, 谌琛1, 陈亮1
1.中国科学院半导体研究所 人工神经网络实验室,北京100083；
2.中国科学院 光电研究院，北京 100094
Author(s):
ZHAO Huimin1, LI Weijun1, LIU Yangyang2, CHEN Chen1, CHEN Liang1
1. Laboratory of Artificial Neural Networks, Institute of Semiconductors, Chinese Academy of Sciences, Beijing 100083, China;
2. The Institute of OptoElectronics, Chinese Academy of Sciences, Beijing 100094, China
关键词:
三高斯模型; 指纹增强; 非经典感受野; 单边滤波
Keywords:
triGaussian model;  fingerprint enhancement;  concentric receptive field;  unilateral filter
分类号:
TP18；TN911.73
文献标志码:
A
摘要:
低质指纹图像在司法刑侦过程中普遍存在，往往需要人工参与鉴别．因此，符合人类视觉特性的指纹图像处理方法研究具有一定的实用价值．将非经典感受野三高斯数学模型引入指纹图像处理，提出一种新的低质指纹图像增强算法．首先通过三高斯单边滤波获得邻域图像的主观感觉亮度；然后对指纹图像进行局部对比度增强．通过分析研究指纹脊谷交替分布的特性，结合三高斯模型自身特性，得到针对指纹图像的三高斯单边滤波的参数自适应模型和局部对比度调整参数．对比实验结果表明，该方法取得了整体和局部的亮度增强效果，突出灰暗区域的细节特征，尤其适用于低质指纹图像的处理．
Abstract:
Low quality fingerprint recognition is an allpervading problem of criminal investigation, which asks for extra manual efforts to address. Therefore, the fingerprint image processing method in accordance with human visual characteristics has certain practical value. This paper introduces the triGaussian model of the concentric receptive field to the fingerprint image processing, and proposes a novel image enhancement algorithm especially for lowquality fingerprint image processing. The algorithm goes like this: firstly obtain the perceptual luminance of the neighbouring image by triGaussian unilateral filtering; and then enhance the local contrast of the given fingerprint image. Based on analysis of the ridgevalley alternatedly distributing properties of fingerprint images and the disinhibitory properties of concentric receptive field, we have obtained the adaptive parameter model of triGaussian unilateral filter especially for fingerprint images as well as the local contrast adjustment parameters. The contrast experiments indicate that the proposed method is effective to enhance the global and local luminance, stress the details of dark areas, and especially appropriate to assist the lowquality fingerprint identification.
参考文献/References:
［1］MALTONI D, MAIO D, JAIN A K, et al. Handbook of fingerprint recognition［M］. 2nd ed. London: SpringerVerlag, 2009: 131133.
［2］HONG L, WAN Y, JAIN A K. Fingerprint image enhancement: algorithms and performance evaluation［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(8): 777789.
［3］KIM B G, PARK D J. Adaptive image normalisation based on block processing for enhancement of fingerprint image［J］. Electronics Letters, 2002, 38(14): 696698.
［4］ZHIXIN S, GOVINDARAJU V. Fingerprint image enhancement based on skin profile. Approximation［C］//Proc Int Conf on Pattern Recognition. Hong Kong, China, 2006, 3: 714717.
［5］GONZALEZ R C, WOODS R E. Digital image processing［M］. 2nd ed. Beijing: Publishing House of Electronics Industry, 2003: 7888.
［6］WIN Z M, SEIN M M. Fingerprint recognition system for low quality images［C］//SICE Annual Conference 2011. Tokyo, Japan, 2011: 11331139. 
［7］AKRAM M U, AYAZ A, IMTIAZ J. Morphological and gradient based fingerprint image segmentation［C］//2011 International Conference on Information and Communication Technologies(ICICT). Karachi, Pakistan, 2011: 14.
［8］MA J, JING X J, ZHANG Y Y. Simple effective fingerprint segmentation algorithm for low quality images［C］//2010 3rd IEEE International Conference on Broadband Network and Multimedia Technology (ICBNMT). Beijing, China, 2010: 855859.
［9］GREENBERG S, ALADJEM M, KOGAN D. Fingerprint image enhancement using filtering techniques［J］. RealTime Imaging, 2002, 8(3): 227236.
［10］LI C Y, PEI X. Role of the extensive area outside the xcell receptive field in brightness information transmission［J］. Vision Research, 1991, 31(9): 15291540.
［11］金小贤，李卫军，陈旭，等. 一种基于视觉特性的仿生图像增强算法［J］. 计算机辅助设计与图形学学报, 2010, 22(3): 534537. 
JIN Xiaoxian, LI Weijun, CHEN Xu, et al. Study on biomimetic processing method of face image［J］. Journal of ComputerAided Design and Computer Graphics, 2010, 22(3): 534537.
相似文献/References:
[1]谌琛,李卫军,陈亮,等.一种自适应的仿生图像增强方法：LDRF算法[J].智能系统学报,2012,7(5):404.
　CHEN Chen,LI Weijun,CHEN Liang,et al.An adaptive biomimetic image processing method: LDRF algorithm[J].CAAI Transactions on Intelligent Systems,2012,7():404.

备注/Memo

收稿日期： 2012-04-06.
网络出版日期：2012-11-16.
基金项目：国家自然科学基金重大研究计划资助项目（90920013）.
通信作者：李卫军.
E-mail：wjli@semi.ac.cn．
作者简介：
赵慧敏，女，1988年生，硕士研究生，主要研究方向为图像处理与模式识别新理论、新方法.
李卫军，男，1975年生，副研究员，主要研究方向为图像处理、模式识别、智能信息处理，发表学术论文多篇. 
刘扬阳，女，1976年生，副研究员，主要研究方向为光电成像技术与图像处理、模式识别，发表学术论文多篇.

更新日期/Last Update: 2013-03-19
Copyright © 《 智能系统学报》 编辑部
地址：（150001）黑龙江省哈尔滨市南岗区南通大街145-1号楼 电话：0451- 82534001、82518134　邮箱：tis@vip.sina.com