Online signature verification based on signatures turning angle representation using longest common subsequence matching

Barkoula, Konstantina; Economou, George; Fotopoulos, S.

doi:10.1007/s10032-012-0193-9

Cited by 42 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Dynamic Time Warping (DTW) algorithm [4] was used in order to compute pairwise distances between signatures, while Support Vectors Machines (SVMs) were incorporated in the final stage of decision making. The evolution of several parameters such as position, pressure, azimuth and altitude angle was used in [7,8,12], in order to capture signatures' dynamic properties. Vector quantization algorithms were applied on the feature vectors utilizing user specific codebooks in order to encode and compress the captured data.…”

Section: Introductionmentioning

confidence: 99%

On-line signature recognition via fusion of dynamic features into dissimilarity space

Theodorakopoulos

Economou

Fotopoulos

et al. 2013

IEEE International Symposium on Signal Processing and Information Technology

View full text Add to dashboard Cite

In this paper a method for on-line signature recognition that combines dynamic features, filsed into dissimilarity space, with a powerfitl collaborative sparse representation-based classification scheme is proposed. Dissimilarity vectors are formed in two stages. Initially, a number of informative dynamic features are extracted and stored in sequences. Aflenvards, pairwise dissimilarities among feature sequences, computed using the DTW algorithm, are used to construct the new representation. Based on collaborative sparse representation principles, a new embedding space is defined where classification can be implemented e f ficiently. According to this scheme, signatures are represented in terms of their position inside the data structure, resulting in high-level performance without utilizing optimal feature selection procedures. The proposed framework has been evaluated using the SUSIG and the SVC2004 on-line signature databases.

show abstract

Section: Introductionmentioning

confidence: 99%

On-line signature recognition via fusion of dynamic features into dissimilarity space

Theodorakopoulos

Economou

Fotopoulos

et al. 2013

IEEE International Symposium on Signal Processing and Information Technology

View full text Add to dashboard Cite

show abstract

“…DTW has been used widely to solve the signature verification problem for nearly a decade [9] [13]. TABLE I lists the performance of the different variations of the DTW algorithm on the MCYT-100 dataset.…”

Section: B Dtw Based Online Signature Verificationmentioning

confidence: 99%

On the discrimination power of dynamic features for online signature

Pal

Al-Assam

Sellahewa

2017

2017 22nd International Conference on Digital Signal Processing (DSP)

View full text Add to dashboard Cite

Abstract-The mobile market has taken huge leap in the last two decades, re-defining the rules of communication, networking, socializing and transactions among individuals and organizations. Authentication based on verification of signature on mobile devices, is slowly gaining popularity. Most online signature verification algorithms focus on computing the global Equal Error Rate across all users for a dataset. In this work, contrary to such a representation, it is shown that there are user-specific differences on the combined features and user-specific differences on each feature of the Equal Error Rate(EER) values. The experiments to test the hypothesis is carried out on the two publicly available dataset using the dynamic time warping algorithm. From the experiments, it is observed that for the MCYT-100 dataset, which yields an overall EER of 0.08, the range of user-specific EER is between 0 and 0.27. I. INTRODUCTIONWith the rapid development of touch screen capabilities on mobile devices, virtual transactions and the need to have secure biometric authentication services have also increased. Along with facial recognition, voice recognition, one of the biometric modality that is gaining popularity recently is online signature verification. Signatures have been used to authenticate individuals for over centuries and is a legally accepted biometric trait for authenticating an individual. The fundamental advantage of the signature modality over other biometric modalities (like face, fingerprints etc.) is that it gives the user the control to change their signature in an event of a predicted impending security attack. Signatures are personalized gesture patterns within a finite space. There are two traditional approaches to signature verification: online and offline systems. In an offline system, the image attributes are matched for authenticating an individual [1] while in an online system, dynamic features like the x or y coordinates, pressure, azimuth etc. are used for verification purposes.In this work, it is shown through experiments that different dynamic attributes of a signature contributes differently for every user. The rest of paper is arranged as follows: Section II details the background of online signature verification and the dynamic time warping (DTW) algorithm, Section III methodology of the experiments, Section IV discusses the results of the experiments and Section V consist the conclusions.

show abstract

“…List of common features have been described in Table 1 [5]. Furthermore, some non-common features have been described in other papers [6,9,[11][12][13][14][15]. Recently, some biometric authentication systems for face, iris and fingerprint have been proposed based on deep neural networks which used autoencoders for feature extraction phase [3,16].…”

Section: B Feature Extractionmentioning

confidence: 99%

“…Barkoula, et al [9] studied the signatures Turning Angle Sequence (TAS), the Turning Angle Scale Space (TASS) representations, and their application to online signature verification. In the matching stage, the authors have employed a variation of the longest common sub-sequence matching technique.…”

Section: Classificationmentioning

confidence: 99%

“… Statistical: In this approach, distance-based classifiers can be considered, such as Neural Networks [7], Hidden Markov Models (HMM) [4,8]..  Structural: This approach is related to structural representations of signatures and compared through graph or tree matching techniques [9]. In this paper, a signature verification system has been proposed based on deep learning.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Online signature verification based on feature representation

Fayyaz

Saffar

Sabokrou

et al. 2015

2015 the International Symposium on Artificial Intelligence and Signal Processing (AISP)

View full text Add to dashboard Cite

Abstract-Biometrics systems have been used in a wide range of applications and have improved people authentication. Signature verification is one of the most common biometric methods with techniques that employ various specifications of a signature. Recently, deep learning has achieved great success in many fields, such as image, sounds and text processing. In this paper, deep learning method has been used for feature extraction and feature selection, which has enormous impact on the accuracy of signature verification. This paper presents a method based on self-taught learning, in which a sparse autoencoder attempts to learn discriminative features of signatures from a large unlabeled signature dataset. Then, the features learned are employed to present users' signatures by creating a model for each user based on user genuine signatures. Finally, users' signatures are classified using a one-class classifier. The proposed method is independent on signature datasets thanks to self-taught learning. The features have been learned from 17,500 signatures (ATVS dataset) and verification process of the proposed system is evaluated on SVC2004 and SUSIG signature datasets, which contain genuine and skilled forgery signatures. The experimental results indicate significant error reduction and accuracy enhancement in comparison with state of the art counterparts.

show abstract

Online signature verification based on signatures turning angle representation using longest common subsequence matching

Cited by 42 publications

References 54 publications

On-line signature recognition via fusion of dynamic features into dissimilarity space

On-line signature recognition via fusion of dynamic features into dissimilarity space

On the discrimination power of dynamic features for online signature

Online signature verification based on feature representation

Contact Info

Product

Resources

About