Reducing forgeries in writer-independent off-line signature verification through ensemble of classifiers

In this work we address two important issues of off-line signature verification. The first one regards feature extraction. We introduce a new graphometric feature set that considers the curvature of the most important segments, perceptually speaking, of the signature. The idea is to simulate the shape of the signature by using Bezier curves and then extract features from these curves. The second important aspect is the use of an ensemble of classifiers based on graphometric features to improve the reliability of the classification, hence reducing the false acceptance. The ensemble was built using a standard genetic algorithm and different fitness functions were assessed to drive the search. Two different scenarios were considered in our experiments. In the former, we assume that only genuine signatures and random forgeries are available to guide the search. In the latter, on the other hand, we assume that simple and simulated forgeries also are available during the optimization of the ensemble. The pool of base classifiers is trained using only genuine signatures and random forgeries. Thorough experiments were conduct on a database composed of 100 writers and the results compare favorably.     

基于几何中心静态手写签名的识别算法研究*

研究了静态手写体签名识别和认证的问题。针对静态手写体签名无法提供笔画之间前后时序动态信息和手写笔画的压力信息,提出了一种利用手写签名的几何中心作为特征值的识别和认证算法。首先将静态签名图像依据几何中心不断进行切分,使其成为独立的小块;然后依据各个小块的几何中心的相对位置和距离提取特征值;在此基础上进行签名识别和认证。实验结果显示本方法快速有效,所提取的特征能稳定地描述包含集合形变的手写签名字体。该方法能拓展应用到手写体的识别系统中。     

A hybrid opto-electronic method for fast off-line handwritten signature verification

This paper proposes a hybrid opto-electronic method for the fast automatic verification of handwritten signatures. This method combines several statistical classifiers and consists of three steps. The first step aims to transform the original signatures using the identity and four Gabor transforms. For each image transform, the second step is to intercorrelate the analysed signature with the similarly transformed signatures of the learning database. Finally, the third step performs the verification of the authenticity of signatures by fusing the decisions related to each transform. Image transforms and intercorrelations can be computed in real time using a high-speed optical correlator. The different decisions and their fusion are then digitally performed. The opto-electronic implementation of the proposed method has been simulated on a large database, taking into account the specific constraints of the optical implementation. Satisfactory results have been obtained. Indeed, the proposed system allows the rejection of 62.4% of the forgeries used for the experiments when 99% of genuine signatures are correctly recognized.Received: 19 November 2002, Accepted: 15 June 2004, Published online: 12 August 2004 Correspondence to: J.-B. Fasquel     

离线签名验证中的多分类器集成

在离线签名验证的分类器设计中,为了减少特征向量分布不均和维数过高对实验结果的影响,给出一种多分类器集成的方法.根据特征向量数量级的不同进行分组,各组分类器自适应地确定分类器权重,通过投票表决得出集成判决结果.实验结果表明,通过分组和加权后,分类正确率有明显提高.     

Writer-independent off-line signature verification using surroundedness feature

The paper presents a novel set of features based on surroundedness property of a signature (image in binary form) for off-line signature verification. The proposed feature set describes the shape of a signature in terms of spatial distribution of black pixels around a candidate pixel (on the signature). It also provides a measure of texture through the correlation among signature pixels in the neighborhood of that candidate pixel. So the proposed feature set is unique in the sense that it contains both shape and texture property unlike most of the earlier proposed features for off-line signature verification. Since the features are proposed based on intuitive idea of the problem, evaluation of features by various feature selection techniques has also been sought to get a compact set of features. To examine the efficacy of the proposed features, two popular classifiers namely, multilayer perceptron and support vector machine are implemented and tested on two publicly available database namely, GPDS300 corpus and CEDAR signature database.     

Multi-feature extraction and selection in writer-independent off-line signature verification

Some of the fundamental problems faced in the design of signature verification (SV) systems include the potentially large number of input features and users, the limited number of reference signatures for training, the high intra-personal variability among signatures, and the lack of forgeries as counterexamples. In this paper, a new approach for feature selection is proposed for writer-independent (WI) off-line SV. First, one or more preexisting techniques are employed to extract features at different scales. Multiple feature extraction increases the diversity of information produced from signature images, allowing to produce signature representations that mitigate intra-personal variability. Dichotomy transformation is then applied in the resulting feature space to allow for WI classification. This alleviates the challenges of designing off-line SV systems with a limited number of reference signatures from a large number of users. Finally, boosting feature selection is used to design low-cost classifiers that automatically select relevant features while training. Using this global WI feature selection approach allows to explore and select from large feature sets based on knowledge of a population of users. Experiments performed with real-world SV data comprised of random, simple, and skilled forgeries indicate that the proposed approach provides a high level of performance when extended shadow code and directional probability density function features are extracted at multiple scales. Comparing simulation results to those of off-line SV systems found in literature confirms the viability of the new approach, even when few reference signatures are available. Moreover, it provides an efficient framework for designing a wide range of biometric systems from limited samples with few or no counterexamples, but where new training samples emerge during operations.     

An off-line signature verification system using an extracted displacement function

This paper proposes an off-line signature verification system based on a displacement extraction method. The optimum displacement functions are extracted for any pair of signatures using minimization of a functional. The functional is defined as the sum of the squared Euclidean distance between two signatures and a penalty term requiring smoothness of the displacement function. A coarse-to-fine search method is applied to prevent the calculation from stopping at local minima. Based on the obtained displacement function, the dissimilarity between a questionable signature and the corresponding authentic one is measured. The proposed system achieved error rate of 24.9% in a experiment.     

Improving performance of HMM-based off-line signature verification systems through a multi-hypothesis approach

The neural and statistical classifiers employed in off-line signature verification (SV) systems are often designed from limited and unbalanced training data. In this article, an approach based on the combination of discrete Hidden Markov Models (HMMs) in the ROC space is proposed to improve the performance of these systems. Inspired by the multiple-hypothesis principle, this approach allows the system to select, from a set of different HMMs, the most suitable solution for a given input sample. By training an ensemble of user-specific HMMs with different number of states and different codebook sizes, and then combining these models in the ROC space, it is possible to construct a composite ROC curve that provides a more accurate estimation of system performance. Moreover, in testing mode, the corresponding operating points—which may be selected dynamically according to the risk associated with input samples—can significantly reduce the error rates. Experiments performed by using a real-world off-line SV database, with random, simple and skilled forgeries, indicate that the multi-hypothesis approach can reduce the average error rates by more than 17%, as well as the number of HMM states by 48%.     

A different approach to off-line handwritten signature verification using the optimal dynamic time warping algorithm

In this paper, a method for the automatic handwritten signature verification (AHSV) is described. The method relies on global features that summarize different aspects of signature shape and dynamics of signature production. For designing the algorithm, we have tried to detect the signature without paying any attention to the thickness and size of it. The results have shown that the correctness of our algorithm detecting the signature is more acceptable. In this method, first the signature is pre-processed and the noise of sample signature is removed. Then, the signature is analyzed and specification of it is extracted and saved in a string for the comparison. At the end, using adapted version of the dynamic time warping algorithm, signature is classified as an original or a forgery one.     

一种有效的基于证据理论的离线签名识别方法

提出了一种有效的基于证据理论的离线签名识别方法。从签名图像的3种信息载体中提取出4种特征,利用所提取的4种特征分别构造基于证据理论的k-NN分类器对签名图像进行初步识别,将各k-NN分类器的输出作为证据,用改进的证据理论合成公式融合不同分类器的输出得到最终识别结果。结果表明：该识别方法能有效地提高离线签名的识别率。     

适于数据流组合分类的直推学习方法

在进行组合决策时,已有的组合分类方法需要对多个组合分类器均有效的公共已知标签训练样本。为了解决在没有已知标签样本的情况下数据流组合分类决策问题,提出一种基于约束学习的数据流组合分类器的融合策略。在判定测试样本上的决策时,根据直推学习理论设计满足每一个局部分类器约束度量的方法,保证了约束的可行性,解决了分布式分类聚集时最大熵的直推扩展问题。测试数据集上的实验证明,与已有的直推学习方法相比,此方法可以获得更好的决策精度,可以应用于数据流组合分类的融合。     

Glove-based approach to online signature verification

Utilizing the multiple degrees of freedom offered by the data glove for each finger and the hand, a novel on-line signature verification system using the Singular Value Decomposition (SVD) numerical tool for signature classification and verification is presented. The proposed technique is based on the Singular Value Decomposition in finding r singular vectors sensing the maximal energy of glove data matrix A, called principal subspace, so the effective dimensionality of A can be reduced. Having modeled the data glove signature through its r-principal subspace, signature authentication is performed by finding the angles between the different subspaces. A demonstration of the data glove is presented as an effective high-bandwidth data entry device for signature verification. This SVD-based signature verification technique is tested and its performance is shown to be able to recognize forgery signatures with a false acceptance rate of less than 1.2%.     

On-line signature verification

We describe a method for on-line handwritten signature verification. The signatures are acquired using a digitizing tablet which captures both dynamic and spatial information of the writing. After preprocessing the signature, several features are extracted. The authenticity of a writer is determined by comparing an input signature to a stored reference set (template) consisting of three signatures. The similarity between an input signature and the reference set is computed using string matching and the similarity value is compared to a threshold. Several approaches for obtaining the optimal threshold value from the reference set are investigated. The best result yields a false reject rate of 2.8% and a false accept rate of 1.6%. Experiments on a database containing a total of 1232 signatures of 102 individuals show that writer-dependent thresholds yield better results than using a common threshold.     

OCR applied to an electronic voting system

This paper describes a new electronic secure voting system based on automatic paper ballot reading. It presents how the system is organized, it also describes our OCR system and how it is implemented to read paper ballots, and it ends showing some experimental results. The first step of the OCR system consists in extracting from each character several simple features, which help us to perform distortion processing. These simple features are used to define a key which possibly allows us to identify the character. If this is not the matter and there are several candidates for the obtained key, we need to extract more complex features. This second process is based on the use of floating masks, which are specific for each feature, and on the following of its trajectory through the character stroke. The text was submitted by the authors in English. J.K. Espinosa received MS and PhD degrees in Electrical Engineering from the University of the Basque Country, Spain, in 1989 and 2002, respectively. Since 1989, he has been an assistant professor in Telematic Engineering at the Electronics and Telecommunications Department of the University of the Basque Country. He teaches courses in computer programming, data communication, and computer networks and services. His research interests include digital image processing software, optical character recognition, electronic voting systems, video transmission over the Internet, and telematic applications. I. Goirizelaia is professor in the Electronics and Telecommunication Department at the School of Engineering, University of the Basque Country. He received his electrical engineering degree in 1981 and his PhD in electrical engineering in 1987, both from the University of the Basque Country. He worked for Stanford Research Institute (1983–1985) as an international fellow and for LABEIN research laboratory (1986), and in 1987 he started his own company dedicated to industrial applications of image processing techniques. He was vice president for university enterprise relations of the University of the Basque Country from 1998 to 2000. He was a visiting scientist at the MIT Media Lab for six months in 2004. His research interest is the development of advanced information technology, focusing on teleeducation, web based learning environments, and electronic voting technology. He is also interested in security schemes based on image processing algorithms applied to watermarking of digital images. Currently, he is vice president of the University of the Basque Country. J.J. Igarza received his MS degree in 1986 from the Physics Faculty and his MS degree in software engineering in 1997 from the Engineering School of the University of the Basque Country. From 1986 to 1996, he worked as a researcher for a machine vision company, and since 1997, he has been a lecturer at the Engineering School of Bilbao. His research interests include multimodal biometric databases, on-line and offline signature verification, and human-machine interactions.     

基于时序特征融合的动态签名鉴伪算法

针对现有签名鉴伪方法对高水平伪签名鉴伪准确率低的问题,提出一种基于时序特征融合的动态签名鉴伪算法。首先根据签名者落笔与提笔的时间节点建立动态时间轴,在签名过程中提取笔迹的压力和笔速两类时序特征;然后在两类特征对应数据的基础上构建时序特征融合模型,通过一种多维空间模型相似性度量方法计算待测签名和样本签名的相似度,从而实现签名真伪性鉴别。实验结果表明,与现有算法相比,该方法进一步提高了签名鉴伪的准确率和通用性。     

On-line signature verification using vertical signature partitioning

In this paper we propose a new approach to identity verification based on the analysis of the dynamic signature. Considered problem seems to be particularly important in terms of biometrics. Effectiveness of signature verification significantly increases when dynamic characteristics of the signature are considered (e.g. velocity, pen pressure, etc.). These characteristics are individual for each user and difficult to forge. The effectiveness of the verification on the basis of an analysis of the dynamics of the signature can be further improved. A well-known way is to consider the characteristics of the signature in the sections called partitions. In this paper we propose a new method for identity verification which uses partitioning. Partitions represent time moments of signing of the user. In the classification process the partitions, in which the user created more stable reference signatures during acquisition phase, are more important. Other important features of our method are: using capabilities of fuzzy set theory and development on the basis of them the flexible neuro-fuzzy systems and interpretable classification system for final signature classification. In this paper we have included the simulation results for the two currently available databases of dynamic signatures: free SVC2004 and commercial BioSecure database.     

强不可伪造的在线/离线签名方案

针对标准模型下签名方案效率低的问题,利用目标抗碰撞杂凑函数和变色龙哈希函数,提出了一种在线/离线签名方案。在签名消息到来之前,离线阶段进行重签名的大部分计算,并将这些运算结果保存起来;在签名消息到来时,利用离线阶段保存的数据能在很短的时间内生成消息的在线重签名。在标准模型下,证明了新方案在适应性选择消息攻击下满足强不可伪造性。分析结果表明,新方案在效率上优于已有的标准模型下签名方案,在线签名算法仅需要1次模减法运算和1次模乘法运算,适合于计算能力较弱的低端计算设备。     

应用于课堂场景人脸验证的卷积网络方法研究

对于人脸验证应用于课堂场景的问题,通过教室内的摄像头采集学生图像数据集,然而受光照、姿势和环境因素的影响,采集到的图像质量较低,一般的深度学习模型学习难度很大。针对这些问题,对采集到的图像进行了图像预处理,建立卷积图像分类模型与残差网络图像分类模型,并且修改损失函数,提高学习复杂度,训练出紧凑的人脸特征表达。设置了人脸验证阈值,实现人脸验证。通过实验分析在不同数据集上两个模型的精度,并验证修改的损失函数可改善模型性能,最后结果表明在采集到的图像数据集上正确率最高可以达到99. 97%,通过理论分析和实验证实了设计方法的有效性。