Efficient on-line signature recognition based on multi-section vector quantization

This paper proposes a multi-section vector quantization approach for on-line signature recognition. We have used a database of 330 users which includes 25 skilled forgeries performed by 5 different impostors. This database is larger than those typically used in the literature. Nevertheless, we also provide results from the SVC database. Our proposed system obtains similar results as the state-of-the-art online signature recognition algorithm, Dynamic Time Warping, with a reduced computational requirement, around 47 times lower. In addition, our system improves the database storage requirements due to vector compression, and is more privacy-friendly because it is not possible to recover the original signature using the codebooks. Experimental results reveal that our proposed multi-section vector quantization achieves a 98% identification rate, minimum Detection Cost Function value equal to 2.29% for random forgeries and 7.75% for skilled forgeries.     

Confidence voting method ensemble applied to off-line signature verification

In this paper, a new approximation to off-line signature verification is proposed based on two-class classifiers using an expert decisions ensemble. Different methods to extract sets of local and a global features from the target sample are detailed. Also a normalization by confidence voting method is used in order to decrease the final equal error rate (EER). Each set of features is processed by a single expert, and on the other approach proposed, the decisions of the individual classifiers are combined using weighted votes. Experimental results are given using a subcorpus of the large MCYT signature database for random and skilled forgeries. The results show that the weighted combination outperforms the individual classifiers significantly. The best EER obtained were 6.3 % in the case of skilled forgeries and 2.31 % in the case of random forgeries.     

On-line signature recognition based on VQ-DTW

This paper studies some pattern recognition algorithms for on-line signature recognition: vector quantization (VQ), nearest neighbor (NN), dynamic time warping (DTW) and hidden Markov models (HMM). We have used a database of 330 users which includes 25 skilled forgeries performed by five different impostors. This database is larger than the typical ones found in the literature.Experimental results reveal that our first proposed combination of VQ and DTW (by means of score fusion) outperforms the other algorithms (DTW, HMM) and achieves a minimum detection cost function (DCF) value equal to 1.37% for random forgeries and 5.42% for skilled forgeries. In addition, we present another combined DTW-VQ scheme which enables improvement of privacy for remote authentication systems, avoiding the submission of the whole original dynamical signature information (using codewords, instead of feature vectors). This system achieves similar performance than DTW.     

A Markov chain Monte Carlo algorithm for bayesian dynamic signature verification

Authentication of handwritten signatures is becoming increasingly important. With a rapid increase in the number of people who access Tablet PCs and PDAs, online signature verification is one of the most promising techniques for signature verification. This paper proposes a new algorithm that performs a Monte Carlo based Bayesian scheme for online signature verification. The new algorithm consists of a learning phase and a testing phase. In the learning phase, semi-parametric models are trained using the Markov Chain Monte Carlo (MCMC) technique to draw posterior samples of the parameters involved. In the testing phase, these samples are used to evaluate the probability that a signature is genuine. The proposed algorithm achieved an EER of 1.2% against the MCYT signature corpus where random forgeries are used for learning and skilled forgeries are used for evaluation. An experimental result is also reported with skilled forgery data for learning.     

An efficient low cost approach for on-line signature recognition based on length normalization and fractional distances

This work presents a new proposal for an efficient on-line signature recognition system with very low computational load and storage requirements, suitable to be used in resource-limited systems like smart-cards. The novelty of the proposal is in both the feature extraction and classification stages, since it is based on the use of size normalized signatures, which allows for similarity estimation, usually based on dynamic time warping (DTW) or hidden Markov models (HMMs), to be performed by an easy distance calculation between vectors, which is computed using fractional distance, instead of the more typical Euclidean one, so as to overcome the concentration phenomenon that appears when data are high dimensional. Verification and identification tasks have been carried out using the MCYT database, achieving an EER (common threshold) of 6.6% and 1.8% with skilled and random forgeries, respectively, in the first task and 3.6% of error in the second. The proposed system outperforms DTW-based and HMM-based ones, even though these have proved to be very efficient in on-line signature recognition, with storage requirements between 9 and 90 times lesser and a processing speed between 181 and 713 times greater than the DTW-based systems.     

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.

     

SUSIG: an on-line signature database, associated protocols and benchmark results

We present a new online signature database (SUSIG). The database consists of two parts that are collected using different pressure-sensitive tablets (one with and the other without an LCD display). A total of 100 people contributed to each part, resulting in a database of more than 3,000 genuine signatures and 2,000 skilled forgeries. The genuine signatures in the database are real signatures of the contributors. In collecting skilled forgeries, forgers were shown the signing process on the monitor and were given a chance to practice. Furthermore, for a subset of the forgeries (highly skilled forgeries), this animation was mapped onto the LCD screen of the tablet so that the forgers could trace over the mapped signature. Forgers in this group were also informed of how close they were to the reference signature, so that they could improve their forgery quality. We describe the signature acquisition process and several verification protocols for this database. We also report the performance of a state-of-the-art signature verification system using the associated protocols. The results show that the highly skilled forgery set is significantly more difficult compared to the skilled forgery set, providing researchers with challenging forgeries. The database is available through .     

Online Signature Verification and Recognition: An Approach Based on Symbolic Representation

In this paper, we propose a new method of representing on-line signatures by interval valued symbolic features. Global features of on-line signatures are used to form an interval valued feature vectors. Methods for signature verification and recognition based on the symbolic representation are also proposed. We exploit the notions of writer dependent threshold and introduce the concept of feature dependent threshold to achieve a significant reduction in equal error rate. Several experiments are conducted to demonstrate the ability of the proposed scheme in discriminating the genuine signatures from the forgeries. We investigate the feasibility of the proposed representation scheme for signature verification and also signature recognition using all 16500 signatures from 330 individuals of the MCYT bimodal biometric database. Further, extensive experimentations are conducted to evaluate the performance of the proposed methods by projecting features onto Eigenspace and Fisherspace. Unlike other existing signature verification methods, the proposed method is simple and efficient. The results of the experimentations reveal that the proposed scheme outperforms several other existing verification methods including the state-of-the-art method for signature verification.     

Signature Verification: Increasing Performance by a Multi-Stage System

A serial three stage multi-expert system for facing the problem of signature verification is proposed. The whole decision process is organised into successive stages, each using a very reduced set of features for recognising forgeries and providing information about the reliability of the recognition process. The first expert, adopting only a single global feature, is devoted to the elimination of random and simple forgeries. The second stage receives only those signatures not classified as false by the first stage (i.e. those signatures really genuine or forgeries reproduced in a skilled way), and adopts a single specific feature suitable for isolating skilled forgeries. Both of these two stages employ suitable criteria for estimating the reliability of the performed classification, so that, in case of uncertainty, the signature is forwarded to a final stage which takes the final decision, taking into account the decisions of the previous stages together with the corresponding reliability estimations. The proposed multi-stage automatic signature verification system has been tested on a database of signatures produced by 49 different writers. The experimental analysis highlights the effectiveness of the approach: the proposed system employing only two features, used in distinct moments of the decision process, performs better than other systems, employing larger feature set (including the features used in the proposed system) and performing classification in a single stage.     

HMM-based on-line signature verification: Feature extraction and signature modeling

A function-based approach to on-line signature verification is presented. The system uses a set of time sequences and Hidden Markov Models (HMMs). Development and evaluation experiments are reported on a subcorpus of the MCYT bimodal biometric database comprising more than 7000 signatures from 145 subjects. The system is compared to other state-of-the-art systems based on the results of the First International Signature Verification Competition (SVC 2004). A number of practical findings related to feature extraction and modeling are obtained.     

Signature verification using global and grid features

In this work, algorithms for extracting global geometric and local grid features of signature images were developed. These features were combined to build a multi-scale verification function. This multi-scale verification function was evaluated using statistical procedures. Results indicated that the multi-scale verification function yielded a lower verification error rate and higher reliability than the single-scale verification function using either global geometric or local grid feature representation. The correct verification rate of the multi-scale system was more than 90% in rejecting skilled forgeries and was perfect in rejecting simple forgeries based on a limited database.     

Interval valued symbolic representation of writer dependent features for online signature verification

This work focusses on exploitation of the notion of writer dependent parameters for online signature verification. Writer dependent parameters namely features, decision threshold and feature dimension have been well exploited for effective verification. For each writer, a subset of the original set of features are selected using different filter based feature selection criteria. This is in contrast to writer independent approaches which work on a common set of features for all writers. Once features for each writer are selected, they are represented in the form of an interval valued symbolic feature vector. Number of features and the decision threshold to be used for each writer during verification are decided based on the equal error rate (EER) estimated with only the signatures considered for training the system. To demonstrate the effectiveness of the proposed approach, extensive experiments are conducted on both MCYT (DB1) and MCYT (DB2) benchmarking online signature datasets consisting of signatures of 100 and 330 individuals respectively using the available 100 global parametric features.     

BioSecure signature evaluation campaign (BSEC'2009): Evaluating online signature algorithms depending on the quality of signatures

In this paper, we present the main results of the BioSecure Signature Evaluation Campaign (BSEC'2009). The objective of BSEC'2009 was to evaluate different online signature algorithms on two tasks: the first one aims at studying the influence of acquisition conditions (digitizing tablet or PDA) on systems' performance; the second one aims at studying the impact of information content in signatures on systems' performance. In BSEC'2009, the two BioSecure Data Sets DS2 and DS3 are used for tests, both containing data of the same 382 people, acquired respectively on a digitizing tablet and on a PDA. The results of the 12 systems involved in this evaluation campaign are reported and analyzed in detail in this paper. Experimental results reveal a 2.2% EER for skilled forgeries and a 0.51% EER for random forgeries on DS2; and a 4.97% EER for skilled forgeries and a 0.55% EER for random forgeries on DS3.     

A new set of features for a bimodal system based on on-line signature and speech

In this work, a new set of features is presented for a biometric system based on speech and on-line signature. The feature vector is nonhomogeneous and it comprises using TESPAR DZ coefficients, wavelet energy coefficients and also some additional features resulted from the time domain analysis in the case of speech. A feature selection procedure is then applied to reduce the feature vector dimension. A modified symbols alphabet for the TESPAR DZ method is presented. Experimental results were reported using the SVC2004 database for signature and our own bimodal database BimDB10 (for on-line signature and speech). A feature level fusion strategy was adapted in order to achieve our goals. The results show that the fusion of biometric features brings improvement to the system performance.     

On measuring forgery quality in online signatures

This work proposes a novel measure to quantify the quality of a skilled forgery sample in the online signature framework. Such a quality measure is constructed by adapting our former Personal Entropy to the context of skilled forgeries production. For validation, we confront our quality measure to several types of skilled forgeries (static, dynamic, professional) captured on different acquisition platforms. Indeed, four databases are exploited: MCYT-100, Philips database, BioSecure data subsets DS2 and DS3. We prove the effectiveness of our quality measure to quantify the quality of all types of skilled forgeries available with regards to the performance of three classifiers: a Dynamic Time Warping, a Hidden Markov models and a Gaussian Mixture Model.     

Visual identification by signature tracking

We propose a new camera-based biometric: visual signature identification. We discuss the importance of the parameterization of the signatures in order to achieve good classification results, independently of variations in the position of the camera with respect to the writing surface. We show that affine arc-length parameterization performs better than conventional time and Euclidean arc-length ones. We find that the system verification performance is better than 4 percent error on skilled forgeries and 1 percent error on random forgeries, and that its recognition performance is better than 1 percent error rate, comparable to the best camera-based biometrics.     

On using the Viterbi path along with HMM likelihood information for online signature verification.

This paper describes a system using two complementary sorts of information issuing from a hidden Markov model (HMM) for online signature verification. At each point of the signature, 25 features are extracted. These features are normalized before training and testing in order to improve the performance of the system. This normalization is writer-dependent; it exploits only five genuine signatures used to train the writer HMM. A claimed identity is confirmed when the arithmetic mean of two similarity scores, obtained on an input signature, is higher than a threshold. The first score is related to the likelihood given by the HMM of the claimed identity; the second score is related to the segmentation given by such an HMM on the input signature. A personalized score normalization is also proposed before fusion. Our approach is evaluated on several online signature databases, such as BIOMET, PHILIPS, MCYT, and SVC2004, which were captured under different acquisition conditions. For the first time in signature verification, we show that the fusion of segmentation-based information generated by the HMM with likelihood-based information considerably improves the quality of the verification system. Finally, owing to our two-stage normalization (at the feature and score levels), we show that our system results in more stable client-score distributions across databases and in a better separation between the distributions of client and impostor scores.