基于模糊贴近度的指纹匹配算法研究

低质量指纹图像处理与匹配算法研究的开题报告一、选题背景指纹作为一种独特的生物特征，已经成为了现代生物识别技术中最常用的一种方式。

但是在采集指纹图像的过程中，由于各种原因，例如手指干燥、手指脏等，会导致指纹图像的质量较低，从而给指纹识别带来了一定的困难。

因此，针对低质量指纹图像的处理与匹配算法的研究变得十分重要。

二、研究意义低质量指纹图像处理与匹配算法的研究，对于提高指纹识别的准确性和鲁棒性有重要意义。

通过对低质量指纹图像的处理和匹配，可以提高指纹特征的稳定性和可靠性，并且减少误匹配率，提高指纹识别的精度和效率，进一步提高生物特征识别技术在多个领域的应用。

三、研究内容本研究的重点是低质量指纹图像的处理和匹配算法。

在图像处理方面，本研究将探讨如何对低质量指纹图像进行预处理，以提高图像的质量和对峰值的检测性能，并且对于图像的清晰度、对比度、亮度等问题进行研究。

在匹配算法方面，本研究将基于传统的指纹识别算法，采用特征提取和特征匹配的方式对低质量指纹图像进行匹配，同时考虑到低质量指纹的特殊性，采用更高效的特征提取和匹配算法，以提高匹配的准确性和效率。

四、研究方法本研究将采用文献调研和实验室实验的方式进行。

首先，通过调研相关的文献，掌握最新的关于低质量指纹图像处理和匹配算法的研究进展。

其次，根据对文献分析的结果，设计并实施一系列相关的实验，对处理和匹配算法的效果进行评估和比较，进一步优化算法实现。

五、研究计划第一年：调研相关文献，掌握低质量指纹图像的处理和匹配算法的研究进展，搭建实验环境。

第二年：针对低质量指纹图像处理算法进行深入研究，探究如何预处理低质量指纹图像，以提高图像质量和对峰值的检测性能。

第三年：重点研究低质量指纹图像的匹配算法，研究如何提取更稳定可靠的特征，并采用更高效的匹配算法，提高匹配的准确性和效率。

六、预期成果本研究的预期成果包括以下几个方面：1. 提出一套针对低质量指纹图像处理和匹配的算法方案，有效提高指纹识别的准确率和效率；2. 验证和分析所提出算法的可行性和实用性，并与现有的一些算法进行比较分析；3. 发表相关学术论文，掌握了解相关领域的最新研究方向和动态。

蓝牙4.0标准规范下的模糊指纹定位算法李娟娟;张金艺;张秉煜;同荣俊;唐夏【期刊名称】《上海大学学报（自然科学版）》【年(卷),期】2013(019)002【摘要】蓝牙技术的普及以及蓝牙4.0标准规范的提出,使得利用蓝牙技术实现室内定位具有极其广阔的应用前景.把模糊理论应用于蓝牙室内定位系统,提出一种模糊指纹定位算法.基于该算法的定位过程分为离线和在线两个阶段:离线阶段建立模糊指纹库;在线阶段对手机客户端进行实时模糊决策定位.仿真实验结果表明,该算法的平均定位误差为1.36 m,相比于传统的指纹标定法,其定位精度提高约49％,而计算量缩减至原来的1/c,其中c为模糊聚类类别数.%Popularity of Bluetooth technology and the proposition of Bluetooth Specification Version 4.0 make indoor location have a broad application prospect. The fuzzy theory is applied in indoor location based on Bluetooth, and a fuzzy fingerprint location algorithm is proposed. The location process is divided into two parts: off-line and on-line. A fuzzy fingerprint database is established in the off-line stage, and real-time location of cell phone clients is realized in the on-line stage. Simulation results show that the average location error is 1.36 m. Compared with traditional fingerprint calibration method, location precision is improved by 49% and computation complexity is reduced to 1/c where c is the category number of fuzzy clustering.【总页数】6页(P126-131)【作者】李娟娟;张金艺;张秉煜;同荣俊;唐夏【作者单位】上海大学微电子研究与开发中心,上海200072【正文语种】中文【中图分类】TP391【相关文献】1.基于蓝牙4.0的接近度分类室内定位算法 [J], 莫倩;熊硕2.基于蓝牙信标的k-means指纹定位算法研究 [J], 蔡云骐3.普适环境下基于区间值模糊理论的指纹定位算法 [J], 钱梦竹;杨新凯4.基于融合聚类的蓝牙指纹室内定位算法优化 [J], 张驰;张峰;刘叶楠;赵黎5.蓝牙4.0下接近度分类的室内定位算法分析 [J], 刘业辉因版权原因，仅展示原文概要，查看原文内容请购买。

指纹模糊相似度计算摘要：一、引言二、指纹识别技术简介三、指纹模糊相似度计算方法1.细节点匹配法2.结构匹配法3.基于图像特征的匹配法四、指纹模糊相似度计算的应用领域五、总结正文：一、引言随着科技的快速发展，生物识别技术在众多领域得到了广泛应用，其中指纹识别技术以其高安全性和便捷性受到人们的青睐。

在指纹识别领域，指纹模糊相似度计算是一个关键技术，对于提高识别准确率具有重要意义。

本文将对指纹模糊相似度计算进行探讨，分析其方法和应用领域。

二、指纹识别技术简介指纹识别技术是一种基于个体生物特征的识别技术，通过检测指纹的特征点进行身份验证。

指纹识别过程主要包括指纹图像采集、预处理、特征提取和匹配等环节。

在实际应用中，由于各种原因，如手指湿度、污渍、皮肤粗糙度等，会导致指纹图像质量下降，从而影响识别效果。

因此，研究指纹模糊相似度计算具有重要的实际意义。

三、指纹模糊相似度计算方法1.细节点匹配法细节点匹配法是一种基于指纹细节点的匹配方法，通过对指纹图像中的细节点进行提取和匹配，计算指纹之间的相似度。

常用的细节点匹配算法有Minutiae 匹配算法、Sparse Autocorrelation 匹配算法等。

2.结构匹配法结构匹配法是一种基于指纹整体结构的匹配方法，通过对指纹图像的结构特征进行分析，计算指纹之间的相似度。

常用的结构匹配算法有Fingerprint Image Similarity Calculation 算法、Fingerprint Matching Using Structural Features 算法等。

3.基于图像特征的匹配法基于图像特征的匹配法是一种利用指纹图像的特征参数进行匹配的方法，通过对指纹图像进行频谱变换、小波变换等处理，提取图像特征参数，计算指纹之间的相似度。

常用的基于图像特征的匹配算法有Fingerprint Recognition Based on Image Features 算法、Fingerprint Matching Using Wavelet Transform algorithm 等。

A Fingerprint Recognizer Using FuzzyEvolutionary ProgrammingAbstractA fingerprint recognizing system is built with two principal components: the fingerprint administrator and the fingerprint recognizer. Fingerprints are identified by their special features such as ridge endings, ridge bifurcation, short ridges, and ridge enclosures, which are collectively called the minutiae. The fingerprint administrator uses the method of gray scale ridge tracing backed up by a validating procedure to extract the minutiae of fingerprints. The fingerprint recognizer employs the technique of fuzzy evolutionary programming to match the minutiae of an input fingerprint with those from a database. Experimental results show the methods used are highly effective.1. IntroductionFingerprints have been used for many centuries as a means of identifying people [8,16]. As it is well known that fingerprints of an individual are unique and are normally unchanged during the whole life, the use of fingerprints is considered one of the most reliable methods of personal verification. This method has been widely used in criminal identification, access authority verification, financial transferring confirmation, and many other civilian applications.In the old days, fingerprint recognition was done manually by professional experts. But this task has become more difficult and time consuming, particularly in the case where a very large number of fingerprints are involved. During the past decade, several automatic fingerprint identification systems have been made available to meet the demand of new applications [7,16,20,30]. The methods used in these systems are still far from complete satisfaction, however, due to inaccurate extraction of fingerprint characteristics and ineffective pattern matching procedures, which are the two major tasks of fingerprint identification. The Federal Bureau of Investigation's method of identifying a fingerprint by its set of minutiae is widely used in automatic fingerprint identification systems [7,9,18,21,26]. However, the way of extracting a fingerprint's minutiae differs from system to system. Many systems require some form of image preprocessing such as transforming the fingerprint into a binary image and trimming the image's ridges into single pixel lines, before the detection of minutiae is carried out [2,3,6]. This may cause some loss of information and result in inaccurate detection of the fingerprint's minutiae.The task of matching an input fingerprint's minutiae with those from a database is much more difficult. The existing methods that are based on mathematical approximation and string matching algorithms [4,10] or on relaxation and simulated annealing [1,25] have shown to be rather ineffective and time consuming. The method of discrete Hough transform [23,27] is obviously inappropriate as the search space is continuous. These difficulties stem from possible skin elasticity, different scales, and difference in positions of fingerprints.In this paper, we adopt the method of direct gray scale minutiae detection proposed in [5,15,17,29] improved by a backup validating procedure to eliminate false minutiae. As for minutiae matching, we employed the technique of fuzzy evolutionary programming, which has been used successfully in speaker identification [11], images clustering [12,13], and fuzzy algebraic operations [14]. Experimental results show this approach is also highly effective in fingerprint recognition. The paper is organized as follows. Section 2 discusses the characteristics of fingerprints that are commonly used to identify individuals. The method of extracting these fingerprint characteristics is described in Section 3. Section 4 presents the major component of our fingerprint recognizing system, which employs the technique of fuzzy evolutionary programming to identify a fingerprint. In Section 5, we present some experimental results that justify the methods used. The last section summarizes the paper and indicates some related future works.2. Fingerprint characteristicsA fingerprint is a textural image containing a large number of ridges that form groups of almost parallel curves (Figure 1). It has been established that fingerprint's ridges are individually unique and are unlikely to change during the whole life.Although the structure of ridges in a fingerprint is fairly complex, it is well known [7] that a fingerprint can be identified by its special features such as ridge endings, ridge bifurcation, short ridges, and ridge enclosures. These ridge features are collectively called the minutiae of the fingerprint. It is also reported in [7] that for automatic detection of a fingerprint, it suffices to focus on two types of minutiae, namely ridge endings and bifurcation. Figure 2 shows the forms of various minutiae of a fingerprint.A full fingerprint normally contains between 50 to 80 minutiae. A partial fingerprint may contain fewer than 20 minutiae. According to the Federal Bureau of Investigation [7], it suffices to identify a fingerprint by matching 12 minutiae, but it has been reported that in most cases 8 matched minutiae are enough.3. Minutiae extractionFor convenience, we represent a fingerprint image in reverse gray scale. That is, the dark pixels of the ridges are assigned high values where as the light pixels of the valleys are given low values. Figure 3 shows a section of ridges in this representation.In a fingerprint, each minutia is represented by its location (x, y) and the local ridge direction . Figure 4 shows the attributes of a fingerprint's minutia. The process of minutiae detection starts with finding a summit point on a ridge, then continues by tracing the ridge until a minutia, which can be either a ridge ending or bifurcation, is encountered. Details of these tasks are described in the following subsections.3.1 Finding a ridge summit pointTo find a summit point on a ridge, we start from a point x= (x1, x2) and compute the direction angle b y using the gradient method described in [5,17]. Then the vertical section orthogonal to the direction i s constructed (To suppress light noise, the section gray values are convoluted with a Gaussian weight function). The point in this section with maximum gray level is a summit pointon the nearest ridge.The direction angle a t a point x mentioned above is computed as follows. A 9 9 neighborhood around x is used to determine the trend of gray level change. At each pixel u = (u1, u2) in this neighborhood, a gradient vector v(u) = (v1(u), v2(u)) is obtained by applying the operator h = (h1, h2) withto the gray levels in a neighborhood of u. That is,where y runs over the eight neighboring pixels around u and g(y) is the gray level of pixel y in the image. The angle r epresents the direction of the unit vector t that is(almost) orthogonal to all gradient vectors v. That is, t is chosen so that is minimum.3.2 Tracing a ridgeThe task of tracing a ridge line to detect minutiae is described in the following algorithm. This algorithm also constructs a traced image of the fingerprint. Every time a new summit point of the ridge is found, its location in the traced image is assigned a high gray value and the surrounding pixels are given lower gray levels if they have not been marked.Algorithm 1 (Ridge tracing)Start from a summit point x of a ridge.RepeatCompute the direction angle ϕa t x;Move μp ixels from x along the direction ϕt o another point y;Find the next summit point z on the ridge, which is the local maximum of the section orthogonal to direction a t point y; Set x = z;Until point x is a termination point (i.e. a minutia or offvalid area).Determine if the termination point x is a valid minutia,if so record it.End Algorithm 1There are three criteria used to terminate tracing a ridge. The first stopping condition is that when the current point is out of the area of interest. That is, the current point is within 10 pixels from the border, as experiments show that there are rarely any minutiae close to the edges of the image. The second criterion determines a ridge ending: the section at the current point contains no pixels with gray levels above a pre-specified threshold. In this case, the previous point on the ridge is recorded as a ridge endpoint. The last stopping condition corresponds to the case of a possible bifurcation: the current point is detected to be on another ridge that has been marked on the traced image.Algorithm 1 is backed up by a checking procedure that determines if a termination point is a valid minutia. The procedure is expressed as follows. Algorithm 2 (Elimination of false minutiae)If the current ridge end is close to another ridge end with almost opposite direction, then delete both of them and join the gap, as they are simply broken ends of the same ridge.If the current bifurcation point is close to the end of one of its branch, then delete both of them, as short branch of a bifurcation is normally a result of light noise in the image.If the current termination is close to more than two other terminations, then delete all of them, as they are likely caused by damaged ridges in the image.The above algorithms form one major component of our fingerprint recognizing system, called the Fingerprint Administrator. Figure 7 depicts theuser-interface feature of the Fingerprint Administrator. The input fingerprint image is displayed in the left box, and the result of ridge tracing and detection of minutia is shown in a traced image in the right box. Observe that in the traced image,the ridge summits are shown in black color, their surrounding of five pixels is colored red, and the detected minutiae are marked with yellow tangent vectors. If the Save button is clicked, the coordinates of the detected minutiae and their associated direction angles are saved in a database in the form of linked list.The Fingerprint Administrator is used to extract minutiae of known fingerprints and store them in a database. It is also used to extract minutiae of an input fingerprint for the purpose of identification. Experimental results are reported in Section 5.4. Fingerprint recognitionThe primary purpose of our fingerprint recognizing system is to calculate the matching degree of the target fingerprint with the images in a database and to decide if it belongs to a particular individual. A fingerprint is said to match one image in the database if the degree of matching between its minutiae and that of the image in the database is higher than some pre-specified acceptance level. The method of calculating this matching degree is based on our fuzzy evolutionary programming technique, which is described below.Consider two fingerprints that are represented by their sets of minutiaewhere , for. Observe that the two sets may not have the same number of points, and that the order of thepoints in each set is possibly arbitrary. The principal task is to find a transformationthat transforms the set of minutiae P into the set Q. Here, srepresents a scaling factor, a n angle of rotation, and a translation in thexy-plane. Thus, the transform of a minutia is defined by:Also, in order to calculate the degree of matching, we associate with each minutia F(p) a fuzzy set (also denoted by F(p) for convenience) the membership function ofwhich is defined by:whereand represents a fuzzy subset of the real line defined as follows:Intuitively, we allow some degree of tolerance in matching the minutiae F(p) and q, but this tolerance decreases rapidly when the two minutiae are far apart. The matching degree between two sets F(P) and Q is defined as:The task of finding a transformation F to match two sets of minutiae P and Q consists of two phases. First the rotation angle i s estimated by the following algorithm.A lgorithm 3 (Estimation of rotation)Divide the interval [- π, π] into K subintervals,k = 1,…, K. ，Set up an integer array and a real array，and initialize them to 0. For each i = 1,…, m and each j = 1,…, n doFind an index k such that k ≤ - < k+1;Increment c[k] by 1 and increment [k] by ( - ).Find the index k* such that c[k*] is maximum.Let be defined byHaving established the rotation angle , the remaining parameters s and x, y of the transformation F are estimated by the following algorithm.Algorithm 4 (Fuzzy evolutionary programming)Generate a population ofwhere the parameter values are randomly taken from appropriate intervals.For each k = 1,…, m, compute the fitness:RepeatFor each k = 1,…, m, generate an offspringAlgorithms 3 and 4 form the principal component ofour system: the fingerprint recognizer. The fingerprintrecognizer receives an input fingerprint, calls thefingerprint administrator to extract the fingerprint'sminutiae, then tries to match this set of minutiae withthose in the database, until either a good match is found,or the database is exhausted. Experiments are discussed inthe next section.5. Experimental resultsA number of fingerprints of various types, including plain and tented arch, ulna and radial loop, plain whorl,central pocket whorl, double whorl, and accidental whorl,are fed to the system's fingerprint administrator for minutiae detection. The resulting traced images (as depicted in Figure 7) are manually inspected and the results are shown in Table 1.We note also that the fingerprints' ridges are accurately traced, broken ridges are effectively rejoined,and the short ridges and spur ridges are correctly adjusted.Manual checking confirms that most of those anomalies in the fingerprints are result of light noise, skin cut or distortion. The adjustment was realized by the system's process of eliminating false minutiae (Algorithm 2).A number of fingerprints are taken from the database and are modified by various rotations, resizing, and shifting, for use in testing experiments. We also add random light noise to the test images. The results of the fingerprint recognizer's performance are summarized in Table 2.6. Conclusion and future workWe have presented a fingerprint recognizing system that uses the method of gray scale ridge tracing backed up by a validating procedure to detect fingerprint's minutiae and that employs the technique of fuzzy evolutionary programming to match two sets of minutiae in order to identify a fingerprint. The experimental results show that the system is highly effective with relatively clean fingerprints. However, for poorly inked and badly damaged fingerprints, the system appears to be not so successful. In order to handle those bad types of fingerprints, we are working on the addition of a preprocessing component that also adopts the fuzzy evolutionary approach to reconstruct and enhance the fingerprints before they are processed by the system.Also, it is possible to connect the system with a live fingerprint scanner that obtains a person's fingerprint directly and sends it to the system for identification.These are the objectives of our future work.2、译文一个利用模糊匹配算法的指纹识别系统摘要一个指纹识别系统首先要包括两个部分：指纹管理程序和指纹识别器。

指纹图像对比度模糊增强算法
蔡秀梅
【期刊名称】《现代电子技术》
【年(卷),期】2010(033)016
【摘要】指纹图像采集过程常会造成对比度不强等非线性失真,基于模糊逻辑的处理方法常用于改善指纹图像质量.研究了模糊特征平面增强算法和基于广义模糊算子的图像增强算法,将两种算法应用于指纹图像对比度增强,并对增强结果进行比较分析.实验结果表明,采用这2种方法均可以在一定程度上提高指纹图像低灰度区域和高灰度区域之间的对比度,从而提高图像的质量,使增强后的指纹图像结构更清晰.【总页数】3页(P140-142)
【作者】蔡秀梅
【作者单位】西安邮电学院自动化学院,陕西,西安,710121
【正文语种】中文
【中图分类】TP911-34;TP391.41
【相关文献】
1.图像边界检测的区域对比度模糊增强算法 [J], 王晖;张基宏
2.自适应图像对比度模糊增强算法 [J], 马志峰;史彩成
3.一种基于三维医学图像的对比度模糊增强算法 [J], 田法;郝宁波;薛耿剑;郝重阳;韩培友
4.基于FDCT的低对比度指纹图像增强算法 [J], 王宪;陶重犇;杨国梁
5.图像边界检测区域对比度模糊增强算法rn在轮廓提取中的运用 [J], 王士同;彭维科
因版权原因，仅展示原文概要，查看原文内容请购买。

基于指纹匹配和模糊推理的虚拟定位系统设计黄红益;徐圆;朱群雄【摘要】To get more interactions with real environment and improve the ability in dealing with disaster for participators in emergency drill, a virtual localization system based on fingerprinting and fuzzy inference was proposed.This system ran on the mobile android platforms, a virtual 3D world was constructed according to real scene before gathering WIFI signals' fingerprints by scanning signal sources at different points.The relationships between positions and its' fingerprints were built, these logic relationships were used to simulate the distances between fingerprints.Results of the system indicate that the fingerprint matching algorithm based on fuzzy inference has the ability to represent distances among a series of fingerprints.The virtual reality system gets rid of traditional interactive methods and gives participators great flexibility and the sense of reality.The system has been successfully applied in a visit system in the tech-building in a university and remarkable experience is gained.%为让应急演练过程中参演人员与真实环境进行交互,提升演练过程中灾害的处理水平,提出基于指纹数据和模糊推理的虚拟定位系统.以移动Android设备为平台,根据真实环境构建虚拟三维世界,通过扫描空间环境某一位置的WIFI信号来获取特征指纹,构建指纹特征与坐标位置的映射关系,定位系统根据该逻辑映射进行位置的估计.系统运行结果表明,基于模糊推理的指纹匹配算法能够真实反映距离的远近,虚拟移动平台摆脱了传统的交互方式,提高了移动定位的灵活性和真实感,该系统已经成功运用于某高校大楼的虚拟参观系统,取得了显著的效果.【期刊名称】《计算机工程与设计》【年(卷),期】2017(038)003【总页数】6页(P739-743,783)【关键词】室内定位;指纹匹配;模糊推理;加权质心;虚拟现实【作者】黄红益;徐圆;朱群雄【作者单位】北京化工大学信息科学与技术学院,北京 100029;北京化工大学信息科学与技术学院,北京 100029;北京化工大学信息科学与技术学院,北京 100029【正文语种】中文【中图分类】TP391.9在虚拟应急演练过程中，往往会因为无法提供可靠的环境感知服务而造成人身和财产损失，复杂的建筑物使得传统的GPS无法正常工作[1]。

基于模糊集和方向滤波的指纹图像增强算法
李利;范九伦
【期刊名称】《西安邮电学院学报》
【年(卷),期】2008(013)003
【摘要】针对采集条件造成的部分指纹图像质量差的问题,首先应用模糊增强方式以消除指纹图像的模糊性,然后使用方向滤波增强的方式以平滑断线,消除粘连.通过对FVC2000指纹数据库中的部分低质量指纹图像做增强处理,表明本文算法增强效果较好.
【总页数】4页(P81-84)
【作者】李利;范九伦
【作者单位】西安邮电学院,信息与控制系,陕西,西安,710121;西安邮电学院,信息与控制系,陕西,西安,710121
【正文语种】中文
【中图分类】TP391.4
【相关文献】
1.基于FPGA的方向滤波指纹图像增强算法实现 [J], 罗军;肖芳;毛雪莹;黄启俊;常胜
2.基于方向滤波的指纹图像增强算法 [J], 李欣桐;荆涛;李兴华
3.基于方向滤波的指纹图像增强算法研究 [J], 王科俊;李雪峰;赵玥
4.基于方向滤波的指纹图像增强算法的研究 [J], 张彤;杨秀坤
5.一种改进的基于方向滤波的指纹图像增强算法 [J], 武妍;杨磊
因版权原因，仅展示原文概要，查看原文内容请购买。

指纹图像对比度模糊增强算法作者：蔡秀梅来源：《现代电子技术》2010年第16期摘要:指纹图像采集过程常会造成对比度不强等非线性失真,基于模糊逻辑的处理方法常用于改善指纹图像质量。

研究了模糊特征平面增强算法和基于广义模糊算子的图像增强算法,将两种算法应用于指纹图像对比度增强,并对增强结果进行比较分析。

实验结果表明,采用这2种方法均可以在一定程度上提高指纹图像低灰度区域和高灰度区域之间的对比度,从而提高图像的质量,使增强后的指纹图像结构更清晰。

关键词:指纹; 对比度增强; 模糊特征平面; 广义模糊算子中图分类号:TP911-文献标识码:A文章编号:1004-373X(2010)16-0140-03Algorithms of Fingerprint Image Contrast Enhancement Based on Fuzzy LogicCAI Xiu-mei(School of Automation, Xi'an University of Posts and T elecommunications, Xi’an 710121, China)Abstract: The acquisition process of fingerprint image often causes the nonlinear distortion such as low contrast. The algorithms based on the fuzzy logic are often used to improve the quality of fingerprint image. The image enhancement algorithms based on fuzzy property plane and Generalized Fuzzy Operator (GFO) are researched respectively. They are used to enhance the contrast of fingerprint images. The results of contrast enhancement are analyzed contrastively. The experimental results show that these two methods based on fuzzy logic can increase the contrast between the low gray level area and the high gray level area of a fingerprint image to a certain extent, and make the construct of the fingerprint image more clearly.Keywords: fingerprint; contrast enhancement; fuzzy property plane; generalized fuzzy operator0 引言指纹识别是指指尖表面纹路的脊谷分布模式识别,这种脊谷分布模式是由皮肤表面细胞死亡、角化及其在皮肤表面积累形成的。