Online Signature Verification Research Articles

DeepSign: Deep On-Line Signature Verification

Deep learning has become a breathtaking technology in the last years, overcoming traditional handcrafted approaches and even humans for many different tasks. However, in some tasks, such as the verification of handwritten signatures, the amount of publicly available data is scarce, what makes difficult to test the real limits of deep learning. In addition to the lack of public data, it is not easy to evaluate the improvements of novel proposed approaches as different databases and experimental protocols are usually considered. The main contributions of this study are: i) we provide an in-depth analysis of state-of-the-art deep learning approaches for on-line signature verification, ii) we present and describe the new DeepSignDB on-line handwritten signature biometric public database, iii) we propose a standard experimental protocol and benchmark to be used for the research community in order to perform a fair comparison of novel approaches with the state of the art, and iv) we adapt and evaluate our recent deep learning approach named Time-Aligned Recurrent Neural Networks (TA-RNNs) for the task of on-line handwritten signature verification. This approach combines the potential of Dynamic Time Warping and Recurrent Neural Networks to train more robust systems against forgeries. Our proposed TA-RNN system outperforms the state of the art, achieving results even below 2.0% EER when considering skilled forgery impostors and just one training signature per user.

Automatic Signature Verification in the Mobile Cloud Scenario: Survey and Way Ahead

On-line signature verification is typically carried out with the use of digitizing tablets specifically designed for the aim. So far, stand-alone systems have been mainly inspected, but the current distributed/cloud scenario and the amount of mobile devices in everyday life is calling for a new challenge. Within this scenario, signatures are acquired around the world with different kinds of devices and processed on multiple platforms in order to be verified. Through the paper, the different phases of the signature verification process in the new scenario are presented and the most valuable results are discussed considering the following aspects: accessibility and usability, interoperability, security and performance. Achievements as well as weakness are focused to highlight promising directions for further research and technology development.

Time-series averaging and local stability-weighted dynamic time warping for online signature verification

To meet the recent demands for automated security systems, this study proposes a novel single-template strategy that uses mean templates and local stability-weighted dynamic time warping (LS-DTW) to simultaneously improve the speed and accuracy of online signature verification. Specifically, we adopt a recent time-series averaging method, called Euclidean barycenter-based DTW barycenter averaging (EB-DBA), to obtain an effective mean template set for each feature while preserving intra-user variability among reference samples. We then estimate the local stability of the mean template set by using direct matching points that represent stable signature regions in the DTW warping paths between the mean template set and the references. Subsequently, we boost the discriminative power in the verification phase using the LS-DTW distance measure that incorporates the local stability sequence as the weights for the DTW cost function between the mean template set and a query signature. Finally, we use the public SVC2004 Task2/MCYT-100 online signature datasets and the recent 3DAirSig in-air signature dataset to conduct experiments, whose results confirm the effectiveness of the proposed method in both the random- and skilled-forgery scenarios.

DeepFuseOSV: online signature verification using hybrid feature fusion and depthwise separable convolution neural network architecture

Online signature verification (OSV) is a widely utilised technique in the medical, e-commerce and m-commerce applications to lawfully bind the user. These high-speed systems demand faster writer verification with a limited amount of information along with restrictions on training and storage cost. This study makes two major contributions: (i) A competent feature fusion technique in which traditional statistical-based features are fused with deep representations from a convolutional auto-encoder; and (ii) a hybrid architecture combining depth-wise separable convolution neural network (DWSCNN) and long short term memory (LSTM) network delivering state-of-the-art performance for OSV is proposed. DWSCNN is utilised for extracting deep feature representations and LSTM is competent in learning long term dependencies of stroke points of a signature. This hybrid combination accomplishes better classification accuracy (lower error rates) even with one-shot learning, i.e. achieving higher classification accuracies with only one training signature sample per user. The authors have extensively evaluated their model using three widely used datasets MCYT-100, SVC and SUSIG. These exhaustive experimental studies confirm that the DeepFuseOSV framework results in the state-of-the-art outcome by achieving an equal error rate (EER) of 13.26, 2.58, 0.07% in Skilled 1, Skilled 10 and Random 10 categories of MCYT-100, respectively, 7.71% in Skilled 1 category of SVC, 1.70% in Random 1 category of SUSIG.

OSVFuseNet: Online Signature Verification by feature fusion and depth-wise separable convolution based deep learning

Online Signature Verification (OSV) techniques have been deployed in production systems for decades, yet training the model for efficient classification of the test signature from fewer training signature samples is still an open challenge. The advancements in Convolutional Neural Networks (CNNs) enormously boosted the effectiveness of OSV systems. However, learning subtle and discriminating representations from few training samples to classify the genuineness of test signature has not been explored fully. In this paper, a Convolution Autoencoder (CAE) is used to obtain high-level feature representations from the input signature and these high level features are fused with handcrafted features to constitute a hybrid feature set. The hybrid set of features is presented as an input to an Online Signature Verification framework made up of Depth-wise Separable Convolutional Neural Network (DWSCNN). DWSCNN effectively learn deep feature representations with fewer training samples and parameters than traditional CNNs resulting in a light weight OSV framework. Thorough experimental analysis on three benchmark datasets MCYT-100 (DB1), SVC-2004-Task2 and SUSIG-Visual corpus confirm that the proposed hybrid fusion of feature set and DWSCNN based OSV framework achieve higher classification accuracies and outperforms many contemporary and state-of-the art OSV models.

An Algorithm for the Evolutionary-Fuzzy Generation of on-Line Signature Hybrid Descriptors

Abstract In biometrics, methods which are able to precisely adapt to the biometric features of users are much sought after. They use various methods of artificial intelligence, in particular methods from the group of soft computing. In this paper, we focus on on-line signature verification. Such signatures are complex objects described not only by the shape but also by the dynamics of the signing process. In standard devices used for signature acquisition (with an LCD touch screen) this dynamics may include pen velocity, but sometimes other types of signals are also available, e.g. pen pressure on the screen surface (e.g. in graphic tablets), the angle between the pen and the screen surface, etc. The precision of the on-line signature dynamics processing has been a motivational springboard for developing methods that use signature partitioning. Partitioning uses a well-known principle of decomposing the problem into smaller ones. In this paper, we propose a new partitioning algorithm that uses capabilities of the algorithms based on populations and fuzzy systems. Evolutionary-fuzzy partitioning eliminates the need to average dynamic waveforms in created partitions because it replaces them. Evolutionary separation of partitions results in a better matching of partitions with reference signatures, eliminates dispro-portions between the number of points describing dynamics in partitions, eliminates the impact of random values, separates partitions related to the signing stage and its dynamics (e.g. high and low velocity of signing, where high and low are imprecise-fuzzy concepts). The operation of the presented algorithm has been tested using the well-known BioSecure DS2 database of real dynamic signatures.

Role of sub-trajectories in online signature verification

In this paper, we have provided a partitioned based technique which can increase the efficiency of an existing technique in which each partition is called as a sub-trajectory. To implement it, eighty features are extracted from signature trajectories and categorized into four feature sets as static, kinematics, structural and statistical. We have used these four feature categories and their possible combinations on two different algorithms. An important outcome is observed as the EER decreases with increase in sub-trajectories to an optimum level and behaves in reverse direction afterwards which suggests that for any matching algorithm, the present technique can further reduce the error rate to an optimum level. These experiments are performed on the benchmark database SVC 2004 TASK 2 which contains forty genuine signatures of each forty writers and forty skilled forgeries from five different writers. The experiments are discussed in detail for change in the EER with change in each subsequent sub-trajectory level for all feature sets and the results prove that the technique using sub-trajectories improving the EER by a significant average amount of 1.18 with increase in one sub-trajectory level for all the eighty features and 1.5 for the features of categories kinematics and structural when taken together.

Preprocessing approaches in DTW based online signature verification

Abstract Amongst different approaches, dynamic time warping has shown promising results during the online signature verification competitions of previous years. To improve the results of dynamic time warping, different preprocessing steps may be applied and different dimensions of the samples may be compared. The choice of preprocessing steps and comparing dimensions may significantly influence the results. Thus, to aid researchers with these decisions, a comparison made between the results of promising preprocessing algorithms as horizontal scaling, vertical scaling and alignment using dynamic time warping in different dimensions and their combinations on two datasets (SVC2004 and MCYT-100). The results showed that preprocessing methods made a very promising improvement in the verification accuracy.

Signature Verification Using Critical Segments for Securing Mobile Transactions

The explosive usage of mobile devices enables conducting electronic transactions involving direct signature on such devices. Thus, user signature verification becomes critical to ensure the success deployment of online transactions such as approving legal documents and authenticating financial transactions. Existing approaches mainly focus on user verification targeting the unlocking of mobile devices or performing continuous verification based on a user's behavioral traits. Few studies provide efficient real-time user signature verification. In this work, we propose a critical segment based online signature verification system to secure mobile transactions on multi-touch mobile devices. Our system identifies and exploits the segments which remain invariant within a user's signature to capture the intrinsic signing behavior embedded in each user's signature. Our system extracts useful features from a user's signature that describe both the geometric layout of the signature as well as behavioral and physiological characteristics in the user's signing process. Given the input signatures for user enrollment, our system further designs a quality score to identify the problematic signature sets to achieve robust user signature profile construction. Moreover, we develop the signature normalization and interpolation methods to achieve robust signature verification in the presence of signature geometric distortions caused by different writing sizes, orientations and locations on touch screens. Our experimental evaluation of 25 subjects over six months time period shows that our system is highly accurate in provide signature verification and robust to signature forging attacks.

Exploiting complexity in pen- and touch-based signature biometrics

Biometric signature verification has been traditionally performed in pen-based office-like scenarios using devices specifically designed for acquiring handwriting. However, the high deployment of devices such as smartphones and tablets has given rise to new and thriving scenarios for signature biometrics where handwriting can be performed using not only a pen stylus but also the finger via touch interaction. Some preliminary studies have highlighted the challenge of this new scenario and the necessity of further research on the topic. The main contribution of this work is to propose a new on-line signature verification architecture adapted to the signature complexity in order to tackle this new and challenging scenario. Additionally, an exhaustive comparative analysis of both pen- and touch-based scenarios using our proposed methodology is carried out along with a review of the most relevant and recent studies in the field. Significant improvements of biometric verification performance and practical insights are extracted for the application of signature verification in real scenarios.

Online signature verification using single-template matching with time-series averaging and gradient boosting

In keeping with recent developments in artificial intelligence in the era of big data, there is a demand for online signature verification systems that operate at high speeds, provide a high level of security, and allow high tolerances while achieving sufficient performance. In response to these needs, the present study proposes a novel, single-template strategy using a mean template set and weighted multiple dynamic time warping (DTW) distances for a function-based approach to online signature verification. Specifically, to obtain an effective mean template for each feature while reflecting intra-user variability between all the reference samples, we adopt a novel time-series averaging method based on Euclidean barycenter-based DTW barycenter averaging. Then, by using the mean template set, we calculate multiple DTW distances from multivariate time series based on dependent and independent warping. Finally, to boost the discriminative power, we apply a weighting scheme using a gradient boosting model to efficiently combine the multiple DTW distances. Experimental results using the common SVC2004 Task1/Task2 and MCYT-100 signature datasets confirm that the proposed method is effective for online signature verification.

Online Handwritten Signature Verification and Recognition Based on Dual-Tree Complex Wavelet Packet Transform.

Background:With the increasing advancement of technology, it is necessary to develop more accurate, convenient, and cost-effective security systems. Handwriting signature, as one of the most popular and applicable biometrics, is widely used to register ownership in banking systems, including checks, as well as in administrative and financial applications in everyday life, all over the world. Automatic signature verification and recognition systems, especially in the case of online signatures, are potentially the most powerful and publicly accepted means for personal authentication.Methods:In this article, a novel procedure for online signature verification and recognition has been presented based on Dual-Tree Complex Wavelet Packet Transform (DT-CWPT).Results:In the presented method, three-level decomposition of DT-CWPT has been computed for three time signals of dynamic information including horizontal and vertical positions in addition to the pressure signal. Then, in order to make feature vector corresponding to each signature, log energy entropy measures have been computed for each subband of DT-CWPT decomposition. Finally, to classify the query signature, three classifiers including k-nearest neighbor, support vector machine, and Kolmogorov– Smirnov test have been examined. Experiments have been conducted using three benchmark datasets: SVC2004, MCYT-100, as two Latin online signature datasets, and NDSD as a Persian signature dataset.Conclusion:Obtained favorable experimental results, in comparison with literature, confirm the effectiveness of the presented method in both online signature verification and recognition objects.

Reducing the template ageing effect in on‐line signature biometrics

On-line signature recognition is an area of growing interest in recent years due to the massive deployment of high-quality digitising tablets, smartphones, and tablets in many commercial sectors such as banking. In addition, handwritten signature is one of the most socially accepted biometric traits as it has been used in financial and legal agreements for over a century. In this current environment for signature biometrics, the number of stored samples or templates per user can grow very fast, making it possible to train more robust statistical user models, improving the performance of the biometric systems and in particular reducing the template ageing effect. This study carries out an exhaustive experimental analysis of template update strategies for three well-known on-line signature verification approaches, extracts various practical findings related to the template ageing effect in signature biometrics, and configures time-adaptive improved versions of the considered baseline approaches overcoming to some extent the template ageing. The proposed improved approach achieves system performances of 2.1 and 0.2% equal error rate for skilled and random forgery cases, respectively. These results show the efficacy of the proposed methodology.

ASSV

As one kind of biological characteristics of people, handwritten signature has been widely used in the banking industry, government and education. Verifying handwritten signatures manually causes too much human cost, and its high probability of errors can threaten the property safety and even society stability. Therefore, the need for an automatic verification system is emphasized. This paper proposes a device-free on-line handwritten signature verification system ASSV, providing paper-based handwritten signature verification service. As far as we know, ASSV is the first system which uses the changes of acoustic signals to realize signature verification. ASSV differs from previous on-line signature verification work in two aspects: 1. It requires neither a special sensor-instrumented pen nor a tablet; 2. People do not need to wear a device such as a smartwatch on the dominant hand for hand tracking. Differing from previous acoustic-based sensing systems, ASSV uses a novel chord-based method to estimate phase-related changes caused by tiny actions. Then based on the estimation, frequency-domain features are extracted by a discrete cosine transform (DCT). Moreover, a deep convolutional neural network (CNN) model fed with distance matrices is designed to verify signatures. Extensive experiments show that ASSV is a robust, efficient and secure system achieving an AUC of 98.7% and an EER of 5.5% with a low latency.

Development of a System with Online Signature Biometric for Access Control Application

Online signature verification system is a technique based on behavioural biometrics which is gaining popularity for its widespread acceptability due to ease of use and forge proof features. Online (dynamic) signatures are captured from pressure sensitive tablets, signature pads, tablet PCs for further processing. This paper depicts the working mechanism of such a system capable of verifying the true signers as well as detecting the forgery attempt. After the signature data collection, the signatures were preprocessed for future use. A set of total 58 different features (local, global and normalized) were extracted from the online signature data. The system presents a binary classification technique since the test signature is categorized into one of the two classes (genuine or false). Template matching based Dynamic Time Warping (DTW) classifier is used for training and testing purposes with an average recognition rate of 90% for true signers. A separate version of the system was also developed which blocks random and skilled forgeries with a high level of accuracy though the TN rate is higher than the system described here.

Biometric signature authentication using machine learning techniques: Current trends, challenges and opportunities

Biometric systems are playing a key role in the multitude of applications and placed at the center of debate in the scientific research community. Among the numerous biometric systems, handwritten signature verification has got keen interest over the last three decades. Handwritten signature verification is the behavioral bio-metric system that discriminates the genuine signature from the pre-stored known signatures. It has been researched in the number of application areas like banking, financial and business transactions, cheque processing, access control and e-business etc. In this article, we surveyed the techniques of offline and online signature verification systems according to the taxonomy of classification model. A detailed background of signature verification system along with the available datasets are presented comprehensively. At the end, we presented the most notable challenges that guide the readers towards the current trends and future directions of the domain.

Recurrent Adaptation Networks for Online Signature Verification

Online signature verification remains a challenging task owing to large intra-individual variability. To tackle this problem, in this paper, we propose to use recurrent neural networks (RNN) for representation learning in the dynamic time warping framework. Metric-based loss functions are designed explicitly to minimize intra-individual variability and enhance inter-individual variability and to guide the RNN in learning discriminative representations for online signatures. An RNN variant-gated auto regressive units-is proposed and shows a better generalization performance in our framework. Furthermore, we interpret the online signature verification problem as a meta-learning problem: one client is considered as one task, therefore, different clients compose the task space. Based on this formulation, we design an end-to-end trainable meta-layer that learns to adapt to different clients, allowing fast adaptation to new clients in the test stage. In addition, a new descriptor-the length-normalized path signature-is proposed to describe online signatures. Our proposed system achieves a state-of-the-art performance on three benchmark datasets, namely, MCYT-100, Mobisig, and e-BioSign.

A Two-Stage Method for Online Signature Verification Using Shape Contexts and Function Features.

As a behavioral biometric trait, an online signature is extensively used to verify a person’s identity in many applications. In this paper, we present a method using shape contexts and function features as well as a two-stage strategy for accurate online signature verification. Specifically, in the first stage, features of shape contexts are extracted from the input and classification is made based on distance metric. Only the inputs passing by the first stage are represented by a set of function features and verified. To improve the matching accuracy and efficiency, we propose shape context-dynamic time warping (SC-DTW) to compare the test signature with the enrolled reference ones based on the extracted function features. Then, classification based on interval-valued symbolic representation is employed to decide if the test signature is a genuine one. The proposed method is evaluated on SVC2004 Task 2 achieving an Equal Error Rate of 2.39% which is competitive to the state-of-the-art approaches. The experiment results demonstrate the effectiveness of the proposed method.

Dynamic handwritten signature and machine learning based identity verification for keyless cryptocurrency transactions

In this paper we propose a novel system for identity verification by amalgamating online signature verification, machine learning, IOT and blockchain to garner their potentials to cope up and to contain this risk of identity theft specifically in the case of online transactions. In this system signals of roll, pitch and yaw values retrieved from MPU6050 sensor (Inertial Measurement Unit) are analysed using Digital Time Wrapping to obtain DTW minimum distance to verify the identity of the user. In case of cryptocurrencies, we propose a system where private key is not stored anywhere but the same unique private key, assigned to the user by Blockchain, is generated every time with the help of method incorporating biometrics and machine learning. The required data will then be sent to blockchain with the help of IOT system to complete the transaction.

Online signature verification based on string edit distance

Handwritten signatures are widely used and well-accepted biometrics for personal authentication. The accuracy of signature verification systems has significantly improved in the last decade, making it possible to rely on machines in particular cases or to support human experts. Yet, based on only few genuine references, signature verification is still a challenging task. The present paper provides a comprehensive comparison of two prominent string matching algorithms that can be readily used for signature verification. Moreover, it evaluates a recent cost model for string matching which turns out to be particularly well suited for the task of signature verification. On three benchmarking data sets, we show that this model outperforms the two standard models for string matching with statistical significance.