Fingerprint Matching Based on Local Relative Orientation Field

A fingerprint matching method based on local relative orientation field is proposed. It extracts local relative orientation field around each minutia for minutiae matching. Local orientation features are also used to sorting minutiae in order to speed up searching a minutia when pairing minutiae. The experimental result reveals that this method achieves improved recognition accuracy. Key words fingerprint matching - ridge-based minutiae matching - local relative orientation field - sorting minutiae CLC number TP 391 Foundation item: Supported by the National Natural Science Foundation of China (60373023)Biography: ZHU En (1976-), male, Ph. D candidate, research direction: pattern recognition, image processing and information security.

5G Ultra-Dense Network Fingerprint Positioning Method Based on Matrix Completion

The problem of high-precision indoor positioning in the 5G era has attracted more and more attention.A fingerprint location method based on matrix completion(MC-FPL)is proposed for 5G ultradense networks to overcome the high costs of traditional fingerprint database construction and matching algorithms.First,a partial fingerprint database constructed and the accelerated proximal gradient algorithm is used to fill the partial fingerprint database to construct a full fingerprint database.Second,a fingerprint database division method based on the strongest received signal strength indicator is proposed,which divides the original fingerprint database into several sub-fingerprint databases.Finally,a classification weighted K-nearest neighbor fingerprint matching algorithm is proposed.The estimated coordinates of the point to be located can be obtained by fingerprint matching in a sub-fingerprint database.The simulation results show that the MC-FPL algorithm can reduce the complexity of database construction and fingerprint matching and has higher positioning accuracy compared with the traditional fingerprint algorithm.

Efficient Fingerprint Matching Algorithm for Integrated Circuit Cards

Fingerprint matching is a crucial step in fingerprint identification. Recently, a variety of algorithms for this issue have been developed. Each of them is application situation specific and has its advantages and disadvantages. It is highly desired to develop an efficient fingerprint verification technology for Integrated Circuit (IC) Cards or chips. IC cards have some special characteristics, such as very small storage space and slow processing speed, which hinder the use of most fingerprint matching algorithms in such situations. In order to solve this problem, the paper presents an improved minutia-pattern (minutiae-based) matching algorithm by employing the orientation field of the fingerprint as a new feature. Our algorithm not only inherits the advantages of the general minutia-pattern matching algorithms, but also overcomes their. disadvantages. Experimental results show that the proposed algorithm can greatly improve the performance of fingerprint matching in both accuracy and efficiency, and it is very suitable for applications in IC cards.

Evaluation preparation technology of Xiaochaihu granules using fingerprint-peak pattern matching

An approach was proposed to evaluate preparation technology by means of fingerprint-peak matching technology of high performance liquid chromatography with diode array detector （HPLC-DAD）. Similarity and hierarchical clustering analysis （HCA） were applied to identify the 15 batches of Xiaochaihu granules from different manufacturers and our laboratory, and peak pattern matching between the composite formulae and Radix Bupleuri Chinensis, which was one of the main ingredients of Xiaochaihu granules, was utilized to evaluate the preparation technology of Xiaochaihu granules via the indexes of the relative deviation of retention time （RT） and UV spectrum feature similarity of their corresponding peaks. Eleven matching peaks were found between Xiaochaihu granules and Radix Bupleuri Chinensis. However, the saikosaponin A and saikosaponin D, which are the important active components in Radix Bupleuri Chinensis, were not found in Xiaochaihu granules from any manufacturers. The peak areas of 11 characteristic peaks of Xiaochaihu granules samples formed a matrix of 11 × 15. The result of HCA showed that Xiaochaihu granules samples were divided into four kinds of category. Xiaochaihu granules samples from the same manufacturer were basically clustered of the same category. The results suggested that the saikosaponin A and saikosaponin D are prone to structural transformation under the condition of decoction and in the presence of the organic acidic components. These active components, existing in raw herb, might transform to a series of non-active secondary saikosaponin due to unfavourable preparation technology. So the conventional decoction-based preparation technology of Xiaochaihu granules might greatly affect its quality and therapeutic effectiveness. This study demonstrates that fingerprint-peak matching technology can not only be used for quality control of this composite formulae, but also provide some guidance for preparation technology of Xiaochaihu granules.

A Fingerprint Minutiae Matching Method Based on Line Segment Vector

Minutiae-based fingerprint matching is the most commonly used in an automatic fingerprint identification system. In this paper, we propose a minutia matching method based on line segment vector. This method uses all the detected minutiae （the ridge ending and the ridge bifurcation） in a fingerprint image to create a set of new vectors （line segment vector）. Using these vectors, we can determine a truer reference point more efficiently. In addition, this new minutiae vector can also increase the accuracy of the minutiae matching. By experiment on the public domain collections of fingerprint images fvc2004 DID set A and DB4 set A, the result shows that our algorithm can obtain an improved verification performance.

K-Means Graph Database Clustering and Matching for Fingerprint Recognition

The graph can contain huge amount of data. It is heavily used for pattern recognition and matching tasks like symbol recognition, information retrieval, data mining etc. In all these applications, the objects or underlying data are represented in the form of graph and graph based matching is performed. The conventional algorithms of graph matching have higher complexity. This is because the most of the applications have large number of sub graphs and the matching of these sub graphs becomes computationally expensive. In this paper, we propose a graph based novel algorithm for fingerprint recognition. In our work we perform graph based clustering which reduces the computational complexity heavily. In our algorithm, we exploit structural features of the fingerprint for K-means clustering of the database. The proposed algorithm is evaluated using realtime fingerprint database and the simulation results show that our algorithm outperforms the existing algorithm for the same task.

Fingerprint Enhancement, Minutiae Extraction and Matching Techniques

Nowadays, it is a new technology era. Fingerprint is necessary identification recognition of citizens. Fingerprint technology has become more popular and connected to human being life and come to replace traditional identification and verifying recognition today. The fingerprint will continue to substitute the ID of citizens as soon as possible in the future. Fingerprint refers to a complex of combination between gap of ridges and valleys on all of the fingertips. Clearer ridges quality is more convenient to analyze who you are and system can recognize your unique identity. Poorer ridges quality image is a significant problem that system has to improve and enhance the images quality before analyzing the results. Dry and wet ridges are the main issues that developers and researchers need to work on as it provides poor quality image. Medium ridge image is a good condition for analysis, but it also needs to be improved. Therefore, fingerprint images have to control the clearer quality and computing minutiae result and then comparing to templates, which stored in the database. The result will display if it is matched but it will not appear when that person has not yet registered. The paper proposed three algorithms to enhance image, extract minutiae and match with fingerprint templates. The first step, is used to enhance the image quality using brightness and Gabor filters on the fingerprint surface to make ridgelines darker. The second step is to extract minutia. It used to convert the images to binary (0 and 1) and process thinning image with Zhang Suen algorithms. Then, the pictures go through the fixing procedure to correct any missed links, error ridges or spurious minutiae that generated by fingerprint algorithms before they undergo final analysis, calculate location of minutiae and the total of the minutiae on the fingerprint surface. The last step is matching algorithms that can be proof of a person identity by comparing minutiae result with those in the database. If a person has already enrolled, the result will confirm.

一种WiFi混合滤波的RSSI室内定位算法

针对接收信号强度指示(RSSI)在基于WiFi的室内定位应用中易受到环境影响出现波动、突变进而导致定位精度降低的问题,提出了一种WiFi混合滤波的RSSI室内定位算法。首先,根据WiFi信号距离衰减模型设计一种自适应阈值滤波器剔除观测信号异常值;然后,根据自适应阈值滤波、卡尔曼(Kalman)滤波、均值(Mean)滤波设计了一种混合滤波算法(ATKM)对RSSI数据进行滤波;最后,提出了一种基于斯皮尔曼-欧几里得距离的加权K近邻算法(SEWKNN)进行位置估计。在真实环境下的实测结果表明,本文提出的ATKM滤波算法能显著降低RSSI信号的波动,提出的SEWKNN算法在室内环境中平均定位误差为1.17 m,在走廊环境中平均定位误差为1.53m,相比传统的WKNN算法平均定位误差分别下降18.18%和16.84%。

基于网格指纹匹配的光伏阵列电弧故障定位方法

考虑到传统的基于电磁辐射(electromagneticradiation,EMR)信号的光伏阵列电弧故障定位方法存在采样条件严苛、定位精度低等问题,提出一种基于网格指纹匹配的电弧故障定位新方法。首先,使用低采样率获取电弧EMR信号,并提取其均方根值作为代表EMR强度的特征指标。然后,利用BP神经网络(backpropagationneural network,BPNN)挖掘辐照度、信号接收距离与电弧EMR信号强度的内在联系,建立预测模型。接着,根据BPNN输出的双天线阵列与电弧间的预测距离,利用三角定位法初步求得电弧所在区域。最后,网格化划分电弧所在区域的光伏组件,生成网格指纹信息,并将预测距离与指纹信息最匹配的网格的中心坐标作为电弧发生位置的最终预测坐标。实验结果表明,所提算法具备良好的定位能力与适应性,对电弧故障定位的平均绝对误差为0.306m,在定位精度与经济性上均优于EMR衰减模型定位法。

基于稳定AP选择的动态室内定位方法

在室内复杂多变环境下,基于接收信号强度指示(Received Signal Strength Indication,RSSI)的位置指纹算法得到了广泛研究。其中,在线阶段的匹配算法通常采用加权K近邻(Weighted K-Nearest Neighbor,WKNN)算法,但该算法往往采用固定k值方法存在较大的定位误差,具有一定的局限性,并且离线阶段构建位置指纹数据库时并没有考虑到无线接入点(Access Point,AP)信号的波动性。因此,存在大量不同AP的冗余信息,对定位效果产生较大影响。针对上述问题,提出一种基于稳定AP选择的动态室内定位方法。首先,通过高斯滤波对RSSI值进行预处理,滤除随机干扰;然后,通过优选AP算法计算AP的稳定度,筛选出关键AP用于定位;最后,利用距离阈值动态调整k值,并对权重系数进行改善,实现了对WKNN算法的改进。实验结果表明,基于稳定AP选择的动态室内定位方法可以有效去除冗余AP信息,并实现动态k值方案,在定位精度上优于K近邻(K-Nearest Neighbors,KNN)算法、加权K近邻算法和改进的加权K近邻算法,平均定位误差分别降低了26.13%、21.29%和9.89%,定位误差在1.5 m内的累积分布概率达到了60.41%,分别提升了25%、16.66%和8.33%,定位效果提升明显。

Fingerprint Representation Methods Based on B-Spline Functions

The global characteristics of a fingerprint image such as the ridge shape and ridge topology are often ignored in most automatic fingerprint verification system. In this paper, a new representative method based on B-Spline curve is proposed to address this problem. The resultant B-Spline curves can represent the global characteristics completely and the curves are analyzable and precise. An algorithm is also proposed to extract the curves from the fingerprint image. In addition to preserve the most information of the fingerprint image, the knot-points number of the B-Spline curve is reduced to minimum in this algorithm. At the same time, the influence of the fingerprint image noise is discussed. In the end, an example is given to demonstrate the effectiveness of the representation method. Key words fingerprint matching - B-spline interpolation - knots detection - parameterization - boundary condition CLC number TP 391. 41 Foundation item: Supported by the National Natural Science Foundation of China (90200400) and Wuhan Technology Committee (991009185G)Biography: Ruan Ke (1979-), male, Master candidate, research direction: digital image processing.

RSSI室内定位在线匹配算法的研究与性能比较

针对在基于WiFi信号强度RSSI进行室内定位的指纹库算法的在线匹配环节中存在的不足,该文利用基于阈值R_(0)动态筛选匹配的指纹点数,提出了一种增强加权k近邻算法(EWKNN).因为阈值R_(0)可以动态筛选指纹库中的样本点,所以能够提高增强加权k近邻算法的适用度和高精度.仿真结果表明:在R_(0)设置恰当的情况下,增强加权k近邻算法的计算量与加权k近邻算法(WKNN)相当,但定位精度更高.

基于人工智能技术的乐曲节拍识别系统设计

为了高精度识别乐曲节拍,设计基于人工智能技术的乐曲节拍识别系统。首先采集乐曲节拍音频信号,对信号实施放大处理,然后采用复倒谱与子串匹配提取音频信号指纹特征,与乐曲数据库指纹进行匹配,根据匹配结果进行乐曲节拍识别,最后测试所设计系统应用性能。测试结果显示:所设计系统可以高精度识别多种乐曲节拍中有效音频信号,漏识率低,具有较高的实际应用价值。

基于多模型协作和反向校验的快速指纹图像检索研究

在生物特征识别领域,指纹识别因其独特性被广泛应用。随着指纹识别场景的普及,逐一匹配指纹不具有实际意义。因此,研究一种快速高效的指纹图像检索识别技术具有重要意义。本文旨在研究指纹细节点的快速检索和精细匹配问题,提出了一种快速高效的指纹检索模型。该模型结合基于区域的细节点特征匹配算法减少噪声干扰,设计粗粒度残差网络提取数据点特征,此外,利用基于卡尔曼滤波的改进遗传算法二次筛选数据样本,最后,利用BEBLID描述符对样本数据进行精准匹配。经过综合分析,本文所提出的模型运行时间较快,内存消耗量较小。

基于Hadoop云平台的矿井指纹定位算法

针对现有矿井指纹定位算法定位精度不高、实时性不强的问题,结合Hadoop云平台技术,提出了一种基于Hadoop云平台的矿井指纹定位算法。该算法首先在指纹特征提取前对矿井中的多基站信号源进行数据预处理,提高指纹特征的可靠性和鲁棒性;其次,利用小波基函数对源指纹信号进行线性变换,并将多个基站信号分解成不同尺度的频带,得到具有代表性的指纹特征向量;再次,将每个待定位的矿工或移动设备信号分解为若干个子信号区域,并逐区域计算待测信号源与特征集之间的相关系数矩阵,根据相关系数矩阵实现指纹信息匹配;最后,利用多普勒效应和信号衰减原理,对每个节点的位置进行估计,获得每个节点的具体位置信息。在国内某矿井进行了定位试验,结果表明:相对于主流的指纹定位算法,所提出的矿井指纹定位算法能够快速、准确地定位矿井中的人或移动设备,具有较高的定位精度和实时性。该算法可以应用于实际的矿井安全监测和管理中,为矿井安全和高效生产提供支持。

基于深度学习的视频指纹快速鲁棒匹配方法

由于视频指纹匹配主要通过手工特征方法获取表层特征信息,导致匹配结果的调和平均值较低。为此,基于深度学习网络,设计视频指纹快速鲁棒匹配方法。针对给定视频提取梯度质心,获取待匹配视频指纹。应用卷积神经网络构建深度学习特征提取模型,得到视频指纹二值化特征,并通过平移、缩放等几何操作变换指纹细节特征。引入分层匹配理念,实现视频指纹快速鲁棒匹配。实验结果显示,此方法的匹配效果较好。

千万人级数据库下相似异源指纹出现情况及排位关系研究

目的选取指纹区域中最具代表性的斗型纹中心区域,旨在探究千万人级数据库中相似异源指纹的出现情况及其与同源指纹的排位关系,阐述相似异源指纹带来的检验鉴定风险。方法选取60枚具有代表性的斗型纹捺印样本,对其中心区域进行不同特征组合的标注,发送至指纹自动识别系统进行指纹查询,在前100位候选队列中查找同源指纹及检视相似异源指纹,并统计其排位关系。结果在900次指纹查询的候选队列中查找到503次同源指纹,检视到474枚相似异源指纹,存在22.6%的相似异源指纹排位在同源指纹之前或其队列中没有出现同源指纹。结论相似异源指纹在当前千万人级指纹数据库中有较高的出现率,且存在一定数量的相似异源指纹排位在同源指纹之前,这将给指纹检验鉴定工作带来较大的风险,需要指纹检验人员在实际工作中提高对相似异源指纹的认识,规避错误鉴定的发生。

基于SR-SURF的岩石显微图像拼接

岩石显微图像拼接是对岩石分析和研究的关键环节,由于岩石显微图像数量多(成百上千张)内容丰富并且包含大量相似易混淆区域,导致拼接速率和配准准确率低,并且多幅图像拼接时会产生误差累积导致拼接错位,针对此问题提出了一种SR-SURF(similar region-SURF)的岩石显微图像拼接方法.首先选用哈希指纹快速提取相似区域(similar region),然后在此区域检测特征点;之后利用改进的RANSAC(random sample consensus)算法剔除错误匹配点;再然后选用最佳模板匹配纠正错误配准图像;最后引入最小二乘法消除单应性矩阵相乘产生的累计误差;实验结果显示本文的算法消除了多幅图像拼接产生的累计误差,解决了拼接错位问题,提高了拼接速率和配准准确率,具有较高的实用价值,推动了岩石薄片的数字化存储进程.

基于点模式特征提取的指纹匹配技术

为了准确识别指纹,采用基于点模式特征提取的指纹匹配技术。选取FVC2002指纹库中的指纹,对指纹图像进行归一化、灰度阈值分割、二值化、细化等预处理后,提取出端点、分叉点等特征点,并将其包含的指纹边缘点、断点等伪特征点去除,然后将提取的指纹特征信息同指纹库中的指纹进行匹配,测试指纹匹配率为94.12%。仿真试验结果表明,该方法具有较好的识别精度,根据试验结果可知匹配率为99.41%。

基于分区匹配和MBAS-RFR的定位算法

针对井下环境复杂及信号波动大导致定位精度低、稳定性差的问题,提出一种基于改进欧氏距离结合余弦相似度分区匹配模型和多任务天牛群优化随机森林(MBAS-RFR)的井下人员定位算法,离线阶段根据AP节点对巷道进行分区处理并选择区域中心点。在线阶段利用改进分区匹配模型对测试点进行区域划分,最后利用MBAS-RFR模型具体定位。仿真结果表明,改进模型平均定位误差为1.55m且在1.5m以内的置信概率为66%,与其它算法相比,上述算法定位精度高,定位稳定性好。