On-line Signature Verification Method Research Articles

Online Signature Biometrics for Mobile Devices.

This paper addresses issues concerning biometric authentication based on handwritten signatures. Our research aimed to check whether a handwritten signature acquired with a mobile device can effectively verify a user's identity. We present a novel online signature verification method using coordinates of points and pressure values at each point collected with a mobile device. Convolutional neural networks are used for signature verification. In this paper, three neural network models are investigated, i.e., two self-made light SigNet and SigNetExt models and the VGG-16 model commonly used in image processing. The convolutional neural networks aim to determine whether the acquired signature sample matches the class declared by the signer. Thus, the scenario of closed set verification is performed. The effectiveness of our method was tested on signatures acquired with mobile phones. We used the subset of the multimodal database, MobiBits, that was captured using a custom-made application and consists of samples acquired from 53 people of diverse ages. The experimental results on accurate data demonstrate that developed architectures of deep neural networks can be successfully used for online handwritten signature verification. We achieved an equal error rate (EER) of 0.63% for random forgeries and 6.66% for skilled forgeries.

A Review - Signature Verification System Using Deep Learning: A Challenging Problem

One of the challenging and effective way of identifying person through biometric techniques is Signature verification as compared to traditional handcrafted system, where a forger has access and also attempt to imitate it which is used in commercial scenarios, like bank check payment, business organizations, educational institutions, government sectors, health care industry etc. so the signature verification process is used for human examination of a single known sample. There are mainly two types of signature verification: static and dynamic. i) Static or off-line verification is the process of verifying an electronic or document signature after it has been made, ii) Dynamic or on-line verification takes place as a person creates his/her signature on a digital tablet or a similar device. As compared, Offline signature verification is not efficient and slow for a large number of documents. Therefore although vast and extensive research on signature verification there is need to more focus and review on the online signature verification method to increase efficiency using deep learning.

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.

Online handwritten signature verification based on association of curvature and torsion feature with Hausdorff distance

The paper presents an efficient on-line signature verification method based on the dynamic features of a given signature. In the proposed approach, curvature and torsion feature are associated with Hausdorff distance measure which can be used in the verification process. In the feature extraction step, the signature trajectory is approximated as a spatial curve. A set of curvature and torsion value of extreme point is computed from both x coordinate, y coordinate and pressure feature so that the dimension of the curve is reduced. Therefore, a new composed signature feature is created for each person. For the obtained feature data, the most distinctive Hausdorff distance is further proposed to calculate the distances of the eight-dimensional feature vector between the test signature and corresponding template signatures for the verification of the test sample. Comprehensive experiments are implemented on three publicly available databases: the SVC2004, SUSIG and MCYT-100 database. A comparison of our results with some recent signature verification methods available in the literature is provided with equal error rate, and the results indicate that the proposed method would better recognize genuine signatures, random and skilled forgeries.

Online handwritten signature verification based on the most stable feature and partition

Existing methods for online signature verification are generally writer independent, as a common set of features is used for all writers during verification. In this paper, we propose a new method of online handwritten signature verification. Our approach is based on the writer dependent feature as well as writer dependent partition. The two decisions namely optimal feature suitable for a writer and a partition to be used for authenticating the writer, they are taken based on the error rate at the training phase. It is difficult for the forger to imitate the shape and dynamic characteristics of the signer at the same time. According to this feature, we propose to decompose signature trajectories depending upon pressure, velocity direction angle, and velocity information and perform verification on the most stable partition. Experimental results demonstrate superiority of our approach in online signature verification in comparison with other schemes.

A Combined Method for On-Line Signature Verification

Abstract A combined method for on-line signature verification is presented in this paper. Moreover, all the necessary steps in developing a signature recognition system are described: signature data pre-processing, feature extraction and selection, verification and system evaluation. NNs are used for verification. The influence of the signature forgery type (random and skilled) over the verification results is investigated as well. The experiments are carried out on SUsig database which consists of genuine and forgery signatures of 89 users. The average accuracy is 98.46%.

FIR signature verification system characterizing dynamics of handwriting features

This paper proposes an online signature verification method based on the finite impulse response (FIR) system characterizing time-frequency characteristics of dynamic handwriting features. First, the barycenter determined from both the center point of signature and two adjacent pen-point positions in the signing process, instead of one pen-point position, is used to reduce the fluctuation of handwriting motion. In this paper, among the available dynamic handwriting features, motion pressure and area pressure are employed to investigate handwriting behavior. Thus, the stable dynamic handwriting features can be described by the relation of the time-frequency characteristics of the dynamic handwriting features. In this study, the aforesaid relation can be represented by the FIR system with the wavelet coefficients of the dynamic handwriting features as both input and output of the system. The impulse response of the FIR system is used as the individual feature for a particular signature. In short, the signature can be verified by evaluating the difference between the impulse responses of the FIR systems for a reference signature and the signature to be verified. The signature verification experiments in this paper were conducted using the SUBCORPUS MCYT-100 signature database consisting of 5,000 signatures from 100 signers. The proposed method yielded equal error rate (EER) of 3.21% on skilled forgeries.

An advanced multi-matcher method for on-line signature verification featuring global features and tokenised random numbers

In this work, we propose a multi-matcher method for on-line signature verification that combines bi-class classifiers and one-class classifiers. Global information is extracted with a feature-based representation and recognized by using an ensemble of classifiers. Moreover, we show that methods based on tokenised pseudo-random numbers and user specific signature features are highly dependent upon a parameter, the hashing threshold; we demonstrate that using an ensemble of classifiers it is possible to solve this problem leading to a considerable performance improvement.

Online signature verification based on null component analysis and principal component analysis

This paper describes a method for stroke-based online signature verification using null component analysis (NCA) and principal component analysis (PCA). After the segmentation and flexible matching of the signature, we extract stable segments from each reference signature in order that the segment sequences have the same length. The reference set of feature vectors are transformed and separated into null components (NCs) and principal components (PCs) by K-L transform. Online signature verification is a special two-category classification problem and there is not a single available forgery set in an actual system. Therefore, it is different from the typical application of PCA in pattern recognition that both NCA and PCA are used to respectively analyze stable and unstable components of genuine reference set. Experiments on a data set containing a total 1,410 signatures of 94 signers show that the NCA/PCA-based online signature verification method can achieve better results. The best result yields an equal error rate of 1.9%.

On‐line signature verification based on subband decomposition by DWT and adaptive signal processing

AbstractThis paper presents an on‐line signature verification method based on the Discrete Wavelet Transform (DWT) and adaptive signal processing. Time‐varying pen‐position signals of the on‐line signature are decomposed into subband signals by using the DWT. Individual features are extracted as high‐frequency signals in subbands. Verification is achieved in each subband by determining whether the adaptive weight converges to unity. The overall verification decision is made by averaging the verification results in lower subbands. Experimental results show that the verification rate was 95% even if the writer was not permitted to refer to his/her own signature or if a forger traced the genuine signature. © 2005 Wiley Periodicals, Inc. Electron Comm Jpn Pt 3, 88(6): 1–11, 2005; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ecjc.20143

Online signature verification using temporal shift estimated by the phase of Gabor filter

A new online signature-verification method using temporal shift estimation is presented. Local temporal shifts existing in signatures are estimated by the differences of the phase outputs of Gabor filter applied to signature signals. In the proposed signature-verification algorithm, an input signature signal undergoes preprocessing procedures including smoothing, size normalization and skew correction, and then its feature profile is extracted from the signature signal. A Gabor filter with the predetermined center frequency /spl omega/ is applied on a feature profile, and a phase profile is computed from the phase output. The feature profile and the phase profile are length normalized and quantized so that a signature code of fixed size is generated. The temporal shifts existing between two signatures are computed by using the differences between the phase profiles. The information about the temporal shifts is used as offsets for comparing the two feature profiles. Therefore, two kinds of dissimilarities are proposed. Temporal dissimilarity is a measure reflecting the amount of total temporal disturbance between the two signatures. The difference between the two signature profiles is computed at each corresponding point pair and is accumulated into temporally arranged feature profile dissimilarity. The decision boundary is represented as a straight line in the dissimilarity space whose two axes are the two dissimilarity measures. The slope and the position of the decision boundary are computed using the distribution of the dissimilarities among the sample signatures involved in the enrollment procedure. The experimental results show that through the compact and fixed size of signature data representation and relatively simple comparison methods, the proposed method can compare signatures 400 times faster than the conventional DP matching based signature-verification method.

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.

STATISTICAL METHODS FOR ON-LINE SIGNATURE VERIFICATION

Three methods for on-line signature verification are discussed in this paper. They are based on statistical models of features that summarize different aspects of signature shape and the dynamics of signature production. Two of the methods are based on the feature statistics of genuine signatures only. Of these two methods, the simpler one using a Euclidean distance error metric was found to have superior performance when tested on a database of 919 genuine signatures and 330 forgeries. Using a procedure for selecting the individual best 10 out of 22 features, the Euclidean distance method correctly classified 99.5% of the genuine signatures, while rejecting 86% of the forgeries. The third method uses statistical properties of the forgeries as well as the genuine signatures to develop a quadratic discriminant rule for classifying signatures. On the basis of the database used in this study, this method was generally better than the simpler Euclidean distance method. At the same 99.5% acceptance of the genuine signatures, the method rejected 90% of the forgeries.