Dynamic Signature Verification Research Articles

Online Handwritten Signature Verification Method Based on Uni-Feature Correlation Coefficient between Signatures

Online handwritten signature verification is a crucial direction of research in the field of biometric recognition. Recently, many studies concerning online signature verification have attempted to improve performance using multi-feature fusion. However, few studies have provided the rationale for selecting a certain uni-feature to be fused, and few studies have investigated the contributions of a certain uni-feature in the multi-feature fusion process. This lack of research makes it challenging for future researchers in related fields to gain inspiration. Therefore, we use the uni-feature as the research object. In this paper, the uni-feature is one of the X and Y coordinates of the signature trajectory point, pen pressure, pen tilt, and pen azimuth feature. Aiming to solve the unequal length of feature vectors and the low accuracy of signature verification when using uni-features, we innovatively introduced the idea of correlation analysis and proposed a dynamic signature verification method based on the correlation coefficient of uni-features. Firstly, an alignment method of two feature vector lengths was proposed. Secondly, the correlation coefficient calculation formula was determined by analyzing the distribution type of the feature data, and then the correlation coefficient of the same uni-feature between the genuine signatures or between the genuine and forged signatures was calculated. Finally, the signature was verified by introducing a Gaussian density function model and combining it with the signature verification discrimination threshold. Experimental results showed that the proposed method could improve the performance of dynamic signature verification based on uni-features. In addition, the pen pressure feature had the best signature verification performance, with the highest signature verification accuracy of 93.46% on the SVC 2004 dataset.

Signature Verification Using Python

Abstract: Each individual has a distinctive signature that is primarily used for personal identification and the confirmation of significant papers orlegal transactions. Static (offline) and dynamic signature verification come in two flavours (online). After a signature has been made, it can be verified using a methodknown as static verification. For a lot of documents, off line signature verification is ineffective and slow. Online biometric personal verification, such as fingerprints, eye scans, etc., has increased in recent years as a way to get over the limitations of offline signature verification. Convolution neural network (CNN)-based offline signature verification is proposed inthis study. We can extract more accurate representations of the image content using a neural network model called CNN. In order to improve categorization, CNN starts with the raw pixel datafrom the image, trains the model, and then automatically extracts the features. CNN's key advantage over its forerunners is that it automatically identifies significant features without human supervision and that it predicts images with the highest degree of accuracy of any algorithm.

Dynamic Signature Verification Technique for the Online and Offline Representation of Electronic Signatures in Biometric Systems

Biometric systems input physical or personal human characteristics for identification, authentication, and security purposes. With the advancement in communication and intelligent security systems, biometrics are programmed to validate electronic signatures (E-signatures) for online and offline authentication. This article introduces a dynamic signature verification technique (DSVT) using mutual compliance (MC) between the security system and the biometric device. The security system is responsible for online and offline signature approval using personal inputs from humans. This personal verification is related to the stored online/offline signatures using certificates provided for authentication. The certificate-based authentication is valid within a session for online representation. Contrarily, this authentication is valid for persons under offline conditions. In this mode of segregation, application-level authentication verification is performed. A conventional tree classifier for dynamic signature verification is used for differentiating online and offline signatures. Moreover, the security metrics—such as signing bit, key, and size—are verified for both modes using classifier learning. For the segregated mode, the validation of the above is required to be unanimous to accelerate the dynamicity. The proposed technique’s performance is analyzed using the authentication success rate, verification failing ratio, verification time, and complexity.

Evolutionary Algorithm for Selecting Dynamic Signatures Partitioning Approach

Abstract In the verification of identity, the aim is to increase effectiveness and reduce involvement of verified users. A good compromise between these issues is ensured by dynamic signature verification. The dynamic signature is represented by signals describing the position of the stylus in time. They can be used to determine the velocity or acceleration signal. Values of these signals can be analyzed, interpreted, selected, and compared. In this paper, we propose an approach that: (a) uses an evolutionary algorithm to create signature partitions in the time and velocity domains; (b) selects the most characteristic partitions in terms of matching with reference signatures; and (c) works individually for each user, eliminating the need of using skilled forgeries. The proposed approach was tested using Biosecure DS2 database which is a part of the DeepSignDB, a database with genuine dynamic signatures. Our simulations confirmed the correctness of the adopted assumptions.

SynSig2Vec: Forgery-Free Learning of Dynamic Signature Representations by Sigma Lognormal-Based Synthesis and 1D CNN.

Handwritten signature verification is a challenging task because signatures of a writer may be skillfully imitated by a forger. As skilled forgeries are generally difficult to acquire for training, in this paper, we propose a deep learning-based dynamic signature verification framework, SynSig2Vec, to address the skilled forgery attack without training with any skilled forgeries. Specifically, SynSig2Vec consists of a novel learning-by-synthesis method for training and a 1D convolutional neural network model, called Sig2Vec, for signature representation extraction. The learning-by-synthesis method first applies the Sigma Lognormal model to synthesize signatures with different distortion levels for genuine template signatures, and then learns to rank these synthesized samples in a learnable representation space based on average precision optimization. The representation space is achieved by the proposed Sig2Vec model, which is designed to extract fixed-length representations from dynamic signatures of arbitrary lengths. Through this training method, the Sig2Vec model can extract extremely effective signature representations for verification. Our SynSig2Vec framework requires only genuine signatures for training, yet achieves state-of-the-art performance on the largest dynamic signature database to date, DeepSignDB, in both skilled forgery and random forgery scenarios. Source codes of SynSig2Vec will be available at https://github.com/LaiSongxuan/SynSig2Vec.

Impact of augmentation methods in online signature verification

AbstractThe aim of this paper is to investigate the impact of selected data augmentation techniques on the learning performance of neural networks for dynamic signature verification. The paper investigates selected data augmentation techniques in deep learning for verification purpose of dynamic signature. Two neural networks were used as classifiers: MLP and LSTM-FCN. Investigation of five selected augmentation methods and experiments were performed on the open source signature database SVC2004. The authors tested both classifiers without augmentation and then with data augmentation for three extensions of the learning set and three sizes of the user database. They presented the results of the experiments in tabular form for each augmentation method. The results were compared with the existing dynamic signature verification methods and given in the paper.

DsDTW: Local Representation Learning With Deep soft-DTW for Dynamic Signature Verification

DsDTW: Local Representation Learning With Deep soft-DTW for Dynamic Signature Verification

Online Signature Verification Using Locally Weighted Dynamic Time Warping via Multiple Fusion Strategies

Online signature verification is the process of using a dynamic signature verification system to confirm the writer’s identity. It can be used as a security system to confirm entrance applications and password substitutes, as well as a forensic tool to assist an expert’s investigation. This study proposes a novel online signature verification system based on a single-template strategy to improve performance in real-world scenarios. It employs discriminative mean signature template sets as well as fusion strategies of multiple local weighting and warping schemes, for dynamic time warping (DTW). The first step is to generate a set of user-specific mean signature templates for each feature using a recent time-series averaging method, namely, Euclidean barycenter-based DTW barycenter averaging. Then, using multiple and direct matching points between the mean signature templates and references for dependent and independent DTW, we obtain a local weighting estimate considering local stability sequences. Furthermore, we develop fusion strategies for calculating locally weighted DTW sets and concatenating them as a feature vector for each warping, followed by the construction of a support vector machine (SVM) classifier. Finally, in the verification phase, we use the single-template technique to compute a discriminative fused score using SVMs between the mean signature template sets and a query sample. The effectiveness of the proposed method is demonstrated by extensive experimental results obtained using three public online signature datasets: SVC2004 Task1/Task2 and MCYT-100.

An Enhanced Dynamic Signature Verification using the X and Y Histogram Features

Dynamic signature verification by using histogram features is a well-known signature forgery detection technique due to its high performance. However, this technique is often limited to angular histograms derived from vectors containing two adjacent points. We propose additional new features from the X and Y histograms to overcome the limitation. Our experiments indicate that our technique produced Under Curve Area AUC values 0.80 to detect skilled forgery and 0.91 for random forgery. Our method performed best when the verification system uses 12 of the most dominant features. This setup produced AUC values of 0.80 to detect skilled forgery and 0.93 for random forgery. These results outperformed the original technique when the X and Y histogram features are not used that produced AUC values of 0.78 to detect skilled forgery and 0.90 for random forgery.

ВЕРИФІКАЦІЯ ТА РОЗПІЗНАВАННЯ ПІДПИСУ ЯК БАГАТОПАРАМЕТРИЧНОГО ПРОЦЕСУ НА ОСНОВІ СПАЙКІНГОВОЇ НЕЙРОННОЇ МЕРЕЖІ

The article reviews the known methods of dynamic signature verification, which are summarized in the classification table. A method of dynamic signature verification based on a spiking neural network is proposed. Three dynamic parameters of the signature l(t), Dα(t), Z(t)  are chosen, which are invariant to the angle of inclination of the signature, and after their normalization - also to the spatial and temporal scales of the signature. These dynamic signature parameters are simultaneously fed to the spiking neural network for recognition in the form of time series without prior conversion into a vector of static features. This, on the one hand, simplifies the method due to the absence of complex computational conversion procedures and, on the other hand, prevents the loss of useful information and therefore increases the accuracy and reliability of signature verification and recognition (especially for forgery signatures that are highly correlated with genuine ones). The used neural network has a simple learning procedure, and not all neurons of the network are trained, but only the output neurons. If you need to add new signatures, you do not need to retrain the entire network, but just add a few output neurons and learn only their connections.

Specimen Authentication System Using Pixel-Based Algorithm

Specimen Authentication is the process used to recognize an individual's handwritten signature. The pre-process of verifying a signature is Pixel-based. There is a need for an automatic verification system for a signature since the signature has been a means of a person's identification for ages. Offline systems work on the scanned image of a signature. The main objective of the study was to design and develop a Specimen Authentication System to examine signatures. In this study, the researchers verify the off-line signatures by taking a boundary of the entire signature and make the pixel comparison. Signature is acquired using a scanner. The detection process is done after the data acquisition and pre-processing. Pre-processing includes noise removal, grey-scale, manipulation, edge detection. Experimental results show that 50% of the accurate matching with the existing one. There is an important distinction between simple signature Comparisons and dynamic signature verification. Both can be computerized, but a Simple comparison only takes into account what the signature looks like. Dynamic signature verification takes into account how the signature was made. With dynamic signature verification, it is not the shape or looks of the meaningful signature; it is the change in speed, pressure, and timing that occur during the act of signing. Consistency created by natural motion and practice over time creates a recognizable pattern that makes the hand-written signature a natural for biometric identification.

Fuzzy Vault Scheme Based on Fixed-Length Templates Applied to Dynamic Signature Verification

As a consequence of the wide deployment of biometrics-based recognition systems, there are increasing concerns about the security of the sensitive information managed. Various techniques have been proposed in the literature for the biometric templates protection (BTP), having gained great popularity the crypto-biometric systems. In the present paper we propose the implementation of a Fuzzy Vault (FV) scheme based on fixed-length templates with application to dynamic signature verification (DSV), where only 15 global features of the signature are considered to form the templates. The performance of the proposed system is evaluated using three databases: a proprietary collection of signatures, and the publicly available databases MCYT and BioSecure. The experimental results show very similar verification performance compared to an equivalent unprotected system.

Dynamic-signature-based user authentication using a fuzzy classifier

Dynamic signature verification is one of the most fast, intuitive, and cost effective tools for user authentication. Dynamic signature recognition uses multiple characteristics in the analysis of an individual’s handwriting. Dynamic characteristics include the velocity, acceleration, timing, pressure, and direction of the signature strokes, all analyzed in the x, y, and z directions. In this paper, the constant term and the first seven harmonics of the Fourier series expansion of the signature were used as features. The authentication systems development includes the following stages: preprocessing, feature selection, classification. Binary metaheuristic algorithms and deterministic algorithms are used to select attributes. The classification was carried out using a fuzzy classifier. The fuzzy classifiers parameters were tuned using continuous metaheuristic algorithms. The efficiency of the authentication system was verified on the author's database. The database contains 280 original variants of the signature of one author and 1281 variants of counterfeit signatures of seven authors. To assess the statistical significance of differences in the accuracy and error rates of the fuzzy classifiers formed by metaheuristic algorithms, the Mann-Whitney (-Wilcoxon) U-test to compare medians and the Kruskal-Wallis test were used.

A Privacy-Preserving Handwritten Signature Verification Method Using Combinational Features and Secure KNN

The handwritten signature is a widely accepted biometric trait for the individual authentication. This paper proposes a secure and dynamic signature verification method which applies to the mobile phone. A key point for signature verification is to extract features of good distinguishability. There are four main steps in our feature extraction process, including preprocessing, attribute generation, attribute truncation and quantization, and feature generation. In addition to the global features that are extracted from the whole signature, we divide a signature into several segments and extract features from these separate regions. The final feature vector is the combination of global and regional features. A user template is constructed by averaging the feature vectors whose elements are scaled by the feature-specific factors. Then, the similarity score of the test signature to the user template can be measured by Euclidean distance. In order to protect the user privacy in a cloud computing scenario, the template and features are further protected by secure kNN which has no influence on signature matching. The performance of the proposed method is demonstrated on the SG-NOTE database acquired by Samsung Galaxy Note and the MCYT-100 database captured by a WACOM pen tablet.

Validating data acquired with experimental multimodal biometric system installed in bank branches

An experimental system was engineered and implemented in 100 copies inside a real banking environment comprising: dynamic handwritten signature verification, face recognition, bank client voice recognition and hand vein distribution verification. The main purpose of the presented research was to analyze questionnaire responses reflecting user opinions on: comfort, ergonomics, intuitiveness and other aspects of the biometric enrollment process. The analytical studies and experimental work conducted in the course of this work will lead towards methodologies and solutions of the multimodal biometric technology, which is planned for further development. Before this stage is achieved a study on the data usefulness acquired from a variety of biometric sensors and from survey questionnaires filled in by banking tellers and clients was done. The decision-related sets were approximated by the Rough Set method offering efficient algorithms and tools for finding hidden patterns in data. Prediction of evaluated biometric data quality, based on enrollment samples and on user subjective opinions was made employing the developed method. After an introduction to the principles of applied biometric identity verification methods, the knowledge modelling approach is presented together with achieved results and conclusions.

Quantifying dynamic time warping distance using probabilistic model in verification of dynamic signatures

One of the multimodal biometric scenarios is realized by considering several features coming from a single biometric entity. Dynamic signature verification has been utilized considering such scenarios. We present a new approach, namely probabilistic dynamic time warping, to verify dynamic signatures where we use dynamic time warping in realizing distance determination in the verification process. Signatures are segmented into several segments, where probability of each segment is quantified with the aid of a relative distance associated with two selected threshold levels. The final decision is achieved by combining all segment probabilities using a Bayes rule. Experiments demonstrate improvement of equal error rate for the proposed approach for the random forgery. The method has been tested on synthetic dataset and two publicly available databases of dynamic signatures, namely SCV2004 and MCYT100.

Online signature verification using double‐stage feature extraction modelled by dynamic feature stability experiment

Identification based on signature verification is one of the most popular biometric methods which were used even prior to the advent of computers. In the field of dynamic signature verification, signatures' time functions (e.g. pen tip velocity, acceleration and pressure) are analysed in addition to static appearance of signatures. Dynamic feature stability (DFS) experiment is a process for finding the most stable signature partitions which are difficult to forge. The experiment can most effectively lead to a focus on the signature trajectories. Due to the different angles related to the signature pad which are regarded as major problem in signature verification algorithms, in this study, radon transform is used to transform rotation effect to shift effect. Convolutional neural network disregards the precise location of image features, as well as shift effects in both axes of image that is decline by its nature. According to DFS experiment, three independent recognition paths are structured and their effects on final classification are determined by the experiment. Three Persian datasets are analysed by DFS, which led to a reliable trait of Persian signatures. As a result, the least verification error is attained. Besides, SVC2004, as an international benchmark is evaluated by the proposed algorithm.

Dynamic Signature Verification System Based on One Real Signature

The dynamic signature is a biometric trait widely used and accepted for verifying a person's identity. Current automatic signature-based biometric systems typically require five, ten, or even more specimens of a person's signature to learn intrapersonal variability sufficient to provide an accurate verification of the individual's identity. To mitigate this drawback, this paper proposes a procedure for training with only a single reference signature. Our strategy consists of duplicating the given signature a number of times and training an automatic signature verifier with each of the resulting signatures. The duplication scheme is based on a sigma lognormal decomposition of the reference signature. Two methods are presented to create human-like duplicated signatures: the first varies the strokes' lognormal parameters (stroke-wise) whereas the second modifies their virtual target points (target-wise). A challenging benchmark, assessed with multiple state-of-the-art automatic signature verifiers and multiple databases, proves the robustness of the system. Experimental results suggest that our system, with a single reference signature, is capable of achieving a similar performance to standard verifiers trained with up to five signature specimens.

Graphical Password-Based User Authentication With Free-Form Doodles

User authentication using simple gestures is now common in portable devices. In this work, authentication with free-form sketches is studied. Verification systems using dynamic time warping and Gaussian mixture models are proposed, based on dynamic signature verification approaches. The most discriminant features are studied using the sequential forward floating selection algorithm. The effects of the time lapse between capture sessions and the impact of the training set size are also studied. Development and validation experiments are performed using the DooDB database, which contains passwords from 100 users captured on a smartphone touchscreen. Equal error rates between 3% and 8% are obtained against random forgeries and between 21% and 22% against skilled forgeries. High variability between capture sessions increases the error rates.

Dynamic signature verification method based on association of features with similarity measures

The paper presents a persons׳ verification method based on the dynamic features of a given signature. In the proposed approach features space is connected with the set of similarity measures which can be used in the signature verification process. Features and linked similarity coefficients create a new composed signature features. Composed features are then reduced in the Hotelling reduction process, where the most appropriate features together with the most distinctive similarity measures are determined for each person. Finally, it leads to reduction of a composed signature features space. Compared to other approaches proposed solution automatically selects the best discriminatory features and similarity measures.The obtained verification results confirm that the proposed method, compared to other verification techniques, is very efficient. Proposed approach has been checked in different experiments, where various classifiers have been taken into consideration – perceptron and Bayesian network based classifiers as well as k-NN, random trees, random forests and others.In this paper we have included the simulation results for the two available datasets of dynamic signatures: SVC2004 and MCYT databases.