Orientation and anisotropy of multi-component shapes from boundary information

We define a method for computing the orientation of compound shapes based on boundary information. The orientation of a given compound shape S is taken as the direction α that maximises the integral of the squared length of projections, of all the straight line segments whose end points belong to particular boundaries of components of S to a line that has the slope α. Just as the concept of orientation can be extended from single component shapes to multiple components, elongation can also be applied to multiple components, and we will see that it effectively produces a measure of anisotropy since it is maximised when all components are aligned in the same direction. The presented method enables a closed formula for an easy computation of both orientation and anisotropy.     

Fingerprint reference point identification based on chain encoded discrete curvature and bending energy

Reference point identification is important in automatic fingerprint recognition system as it can be used to align fingerprints in a correct orientation in spite of the possibility of different transformations in fingerprint images. It is also used in fingerprint classification, as it is desirable to classify fingerprint images for forensic type applications which require the input image to be verified against a large database. The important feature information useful for classification is centered near the reference point. Most of the current approaches for identifying the reference point either require determining ridge orientation or use some complex filters. These methods either operate on 2D (two dimensional) or are not robust to rotation or cannot be applied to every class of fingerprint image. This paper proposes a method to reliably identify unique reference point that operates in 1D (one dimensional). The method treats the fingerprint ridges as a non-overlapped sequence of chain code segments. A modified k-curvature method has been proposed to find the high-curvature area of fingerprint ridges. The reference point localization is based on the property of the ridge’s bending energy. The proposed method is tested on FVC2002 and FVC2004 standard datasets, and the experimental results show that the proposed algorithm can accurately locate reference point for all types of fingerprint images.     

基于隐马尔可夫模型的指纹分类研究

指纹分类是针对大型指纹库的一个重要的索引方式，可以有效地提高指纹匹配的效率．指纹类型的不同表现为指纹纹理结构的差异，而指纹的方向场则可以有效地描述纹理结构的差异．同一类型指纹不同区域上方向角结构的差异以及相邻区域间方向角结构的联系可以视作一个马尔可夫随机场．本文利用嵌入式隐马尔可夫模型对指纹方向场进行建模分析，通过合理地抽取指纹的类型特征，构造观察向量、进行建模训练，然后利用训练好的马尔可夫模型进行匹配，最终提出并实现了一种新的鲁棒性强且精度较高的指纹分类方法．     

An Alternative Approach to Computing Shape Orientation with an Application to Compound Shapes

We consider the method that computes the shape orientation as the direction α that maximises the integral of the length of projections, taken to the power of 2N, of all the straight line segments whose end points belong to the shape, to a line that has the slope α. We show that for N=1 such a definition of shape orientation is consistent with the shape orientation defined by the axis of the least second moment of inertia. For N>1 this is not the case, and consequently our new method can produce different results. As an additional benefit our approach leads to a new method for computation of the orientation of compound objects.     

Global ridge orientation modeling for partial fingerprint identification

Identifying incomplete or partial fingerprints from a large fingerprint database remains a difficult challenge today. Existing studies on partial fingerprints focus on one-to-one matching using local ridge details. In this paper, we investigate the problem of retrieving candidate lists for matching partial fingerprints by exploiting global topological features. Specifically, we propose an analytical approach for reconstructing the global topology representation from a partial fingerprint. First, we present an inverse orientation model for describing the reconstruction problem. Then, we provide a general expression for all valid solutions to the inverse model. This allows us to preserve data fidelity in the existing segments while exploring missing structures in the unknown parts. We have further developed algorithms for estimating the missing orientation structures based on some a priori knowledge of ridge topology features. Our statistical experiments show that our proposed model-based approach can effectively reduce the number of candidates for pair-wised fingerprint matching, and thus significantly improve the system retrieval performance for partial fingerprint identification.     

Multi-algorithmic cancelable fingerprint template generation based on weighted sum rule and <Emphasis Type="Italic">T</Emphasis>-operators

With the emergence of biometric-based authentication systems in real-world applications, template protection in biometrics is a significant issue to be considered in the recent years. This paper presents two feature set computation algorithms, namely nearest neighbor feature set (NNFS) and Delaunay triangle feature set (DTFS), for a fingerprint sample. Further, the match scores obtained from these algorithms are fused using weighted sum rule and T-operators (T-norms and T-conorms). The experimental evaluation done on FVC 2002 databases confirms the credibility of fusion method compared to each individual algorithm used for fusing. The EER obtained for proposed method is 0 %, 0.059 %, and 3.93 % for FVC 2002 DB1, DB2, and DB3 databases, respectively. This paper also aims to prove the effectiveness of applying T-operators for fusion at score level in fingerprint template protection.     

结合迁移学习的轻量级指纹分类模型

目的 目前的指纹分类模型存在操作繁琐、参数较多、所需数据规模大、无法充分利用指纹特征信息等问题,而进行快速准确的指纹分类在大型指纹识别系统中至关重要。方法 传统的机器学习方法大多假设已标注数据与未标注数据的分布是相同的,而迁移学习允许源空间、任务空间在测试集和训练集中的分布是不同的,并且迁移学习仅专注目标任务的训练,使得网络模型根据需求更具个性化。因此,本文提出一种基于迁移学习的轻量级指纹分类模型。该模型结合迁移学习,首先采用梯度估计的方法求取指纹图像的方向场图并且做增强处理;然后将扩展的指纹方向场图数据集用于本文提出的轻量级Finger-SqueezeNet的预训练,使其达到一定的分类效果,从而初步实现网络模型参数的调整;最后保留预训练模型部分的网络参数不变,使用指纹图像数据集NIST-DB4对Finger-SqueezeNet网络进行参数微调（fine tuning）。结果 在使用相同的指纹数据集在本文提出的纯网络模型进行分类训练后发现,未采用迁移学习方法对网络模型进行预训练得到的平均分类结果为93%,而通过预训练后的网络模型可以达到98.45%,最终采用单枚指纹测试的方法得到的测试结果达到95.73%。对比同种类型的方法以及验证标准后可知,本文的指纹分类模型在大幅度减少网络参数的同时仍能达到较高的准确率。结论 采用指纹类内迁移学习方法和轻量级神经网络相结合进行分类,适当利用了指纹特征信息,而且有望使指纹分类模型拓展到移动端。     

基于奇异点的字典模型指纹方向场去噪方法*

方向场估计是指纹识别过程中非常重要的步骤。传统方法如基于梯度的方法等在处理潜指纹图像时很容易受噪音干扰,而最近提出的基于字典模型的方法无法解决“真词错误”的问题。针对上述问题,本文提出一种融合了零极点模型的字典模型的指纹方向场去噪方法,即将指纹方向场看做是零极点控制的方向场和平滑的残差方向场相叠加的结果,通过首先用零极点模型生成正确的零极点控制的方向场,然后用字典模型修正残差方向场方向场,最后将零极点模型生成的方向场与去噪后的残差方向场融合形成重建方向场,通过基于奇异点的字典模型,我们解决了“真词错误”的问题。为了验证算法的有效性,在NIST SD27潜指纹图像数据库上进行了实验。实验结果表明：对于潜指纹,本文算法能获得比字典模型更精确的方向场,继而可以更好地增强潜指纹图像,并在后续的匹配实验中取得更好的结果。     

Fingerprint matching using ridges

Traditionally, fingerprint matching is minutia-based, which establishes the minutiae correspondences between two fingerprints. In this paper, a novel fingerprint matching algorithm is presented, which establishes both the ridge correspondences and the minutia correspondences between two fingerprints. First N initial substructure (including a minutia and adjacent ridges) pairs are found by a novel alignment method. Based on each of these substructure pairs, ridge matching is performed by incrementally matching ridges and minutiae, and then a matching score is computed. The maximum one of the N scores is used as the final matching score of two fingerprints. Preliminary results on FVC2002 databases show that ridge matching approach performs comparably with the minutia-based one.     

一种新的指纹奇异点快速检测方法

作为指纹最重要的全局特征之一,奇异点在基于模型的方向场计算、人工合成指纹、指纹分类、指纹特征匹配等方面发挥了非常重要的作用.在指纹方向场分割的基础上提出了一种称之为方向丰富度的特征,并据此形成了一种新的指纹奇异点快速检测方法.该方法首先将指纹方向场分割为一系列互不重叠的同质区域;然后通过同质区域边缘检测及边缘端点提取实现了奇异点快速定位;最后依据奇异点处方向丰富度特性判断其类型.实验验证了文中算法的有效性.     

Intelligent fingerprint quality analysis using online sequential extreme learning machine

Because the quality of fingerprints can be degraded by diverse factors, recognizing the quality of fingerprints in advance can be beneficial for improving the performance of fingerprint authentication systems. This paper proposes an effective fingerprint quality analysis approach based on the online sequential extreme learning machine (OS-ELM). The proposed method is based not only on basic fingerprint properties, but also on the physical properties of the various sensors. Instead of splitting a fingerprint image into traditional small blocks, direction-based segmentation using the Gabor filter is used. From the segmented image, a feature set which consists of four selected independent local or global features: orientation certainty, local orientation quality, consistency, and ridge distance, is extracted. The selected feature set is robust against various factors responsible for quality degradation and can satisfy the requirements of different types of capture sensors. With the contribution of the OS-ELM classifier, the extracted feature set is used to determine whether or not a fingerprint image should be accepted as an input to the recognition system. Experimental results show that the proposed method performs better in terms of accuracy and time consumed than BPNN-based and SVM-based methods. An obvious improvement to the fingerprint recognition system is achieved by adding a quality analysis system. Other comparisons to traditional methods also show that the proposed method outperforms others.     

Adaptive fingerprint pore modeling and extraction

Sweat pores on fingerprints have proven to be discriminative features and have recently been successfully employed in automatic fingerprint recognition systems (AFRS), where the extraction of fingerprint pores is a critical step. Most of the existing pore extraction methods detect pores by using a static isotropic pore model; however, their detection accuracy is not satisfactory due to the limited approximation capability of static isotropic models to various types of pores. This paper presents a dynamic anisotropic pore model to describe pores more accurately by using orientation and scale parameters. An adaptive pore extraction method is then developed based on the proposed dynamic anisotropic pore model. The fingerprint image is first partitioned into well-defined, ill-posed, and background blocks. According to the dominant ridge orientation and frequency on each foreground block, a local instantiation of appropriate pore model is obtained. Finally, the pores are extracted by filtering the block with the adaptively generated pore model. Extensive experiments are performed on the high resolution fingerprint databases we established. The results demonstrate that the proposed method can detect pores more accurately and robustly, and consequently improve the fingerprint recognition accuracy of pore-based AFRS.     

基于分区模板的重叠指纹分离方法

在刑侦应用中,常需要将现场得到的多个重叠在一起的指纹分离开来。论文提出一种基于分区模板的重叠指纹分离方法。不同类型指纹脊线走向具有特定的模式,定义与每种类型指纹对应的指纹分区模板。这样,将分区模板施用于所对应类型的指纹后,每一分区内的指纹脊线成为走向基本一致的平行曲线。因而采用具有方向和频率选择性的Gabbor滤波器,选择合适的参数,可提取各个区内所要获得的指纹脊线。通过对人工合成图像和现场采集指纹图像的实验结果表明,提出的方案可有效地提取重叠在一起的指纹,保留绝大多数指纹特征点。因此,该文的方案较好地解决了指纹预处理中很少涉及,但在实践中却经常遇到的问题。     

二值指纹图像方向图算法

在指纹自动识别过程中,指纹的纹理特点决定了方向信息的重要性。图像的增强、二值化、分割、模式分类以及压缩等许多地方,都用到了方向信息。方向图是方向信息的表示方法,方向图的准确性决定了自动识别过程中各种算法的效果。本文在二值化处理的基础上,提出了一种不受背景干扰的指纹图像方向图算法,能够准确地反映了指纹模式区的纹理方向。实验证实我们的算法具有良好的鲁棒性,可用于二值化的后期处理。     

Monitoring and diagnosis process of abnormal consumption on smart power grid

Unique and stable reference point is essential for registration and identification in automated fingerprint identification systems. Most existing methods for detecting reference points need to scan the fingerprint image or orientation field pixel by pixel or block by block to confirm a candidate reference point. The inherent complexity of this process makes those methods time-consuming. In this paper, we propose a two-step method to improve the efficiency of detecting reference points by (1) determining the singular point, i.e., the approximate position of the reference point, in a novel fast way; then (2) refining the reference point precisely in the local area of the singular point. In the first step, a walking algorithm is proposed which can walk directly to the singular point without scanning the whole fingerprint image and hence it is extremely fast. Then, in the local area around the singular point, an enhanced method based on mean-shift concept (EMS-based method) is designed to localize the reference point precisely. Experimental results on FVC2000 DB1a and DB2a databases validate that the proposed WEMS (Walking + EMS) method outperforms two state-of-the-art methods in terms of accuracy and efficiency.

     

Singular points detection based on multi-resolution in fingerprint images

The singular points of fingerprints, namely core and delta, play an important role in fingerprint recognition and classification systems. Several traditional methods have been proposed; however, these methods cannot achieve the reliable and accurate detection of poor-quality fingerprints. In this paper, an algorithm is proposed which combines improved Poincaré index and multi-resolution analysis to detect singular points. Conventional Poincaré index method is improved on the basis of the Zero-pole Model analysis to detect singular points with different resolutions. A model is presented to extract the multi-resolution information of the fingerprint pattern; this model divides fingerprint image into nonoverlapping blocks corresponding to different block sizes on the basis of wavelet functions to compute multiple resolution directional fields, and block position shifting is performed on these resolution levels to capture the features of the ridge direction patterns, where the corresponding shifting intervals are based on Sampling theorem. The relationship of singularities detected by improved Poincaré index in different resolution directional fields is used to confirm singular points accurately and reliably. The combination of local and global information makes our algorithm more robust to noise than methods that use local information only, and the existence of this algorithm increases the insight into the nature of singular points extraction. The accuracy and reliability of the method are demonstrated by experiment on database NIST-4, public fingerprint databases FVC02 DB1 and DB2.     

An Optimal Algorithm for the Straight Segment Approximation of Digital Arcs

In this paper, we define the straight segment approximation problem (SSAP) for a given digital arc as that of locating a minimum subset of vertices on the arc such that they form a connected sequence of digital straight segments. Sharaiha (Ph.D. thesis, Imperial College, London, 1991) introduced the compact chord property, and proved its equivalence to Rosenfeld′s chord property (IEEE Trans. Comput. C-23, 1974, 1264-1269). The SSAP is now constrained by the compact chord property, which offers a more convenient geometric representation than the chord property. We develop an O(n²) optimal algorithm for the solution of the SSAP using integer arithmetic. A relaxation of the problem is also presented such that the optimal number of vectors can be reduced according to a user definition. The original algorithm is adapted for the optimal solution of the relaxed problem. An extension to the relaxed problem is also addressed which finds a minimum level of relaxation such that the optimal number of vectors cannot be reduced.     

序列化融合的指纹匹配方法

在指纹识别中,利用细节点或纹线等单一指纹特征的识别算法来得到一个很高的识别性能比较困难。将不同的指纹匹配算法进行融合来获得较高的准确率已经成为当前研究的热点。提出了一种新的序列化融合的指纹匹配方法。利用基于细节点的指纹匹配算法对待识别指纹进行预判,对于不能确定其为同源或异源的,将再利用基于纹线的指纹匹配算法进行匹配,对两次的匹配得分进行融合,基于融合结果判断其为同源或异源。在指纹库FVC2002 DB2上的实验结果表明,采用基于细节点的指纹匹配算法、基于纹线的指纹匹配算法、对上述两种算法的Sum融合方法、提出的方法得到的等错误率（EERs）分别为3.0%、4.9%、2.0%、1.9%,且相对于Sum融合方法,提出的方法在时间消耗上降低了64.64%。