Online Signature Verification Based on Stable Features Extracted Dynamically

Song, Xiaoyu; Xia, Xing‐Hua; Luan, Fangjun

doi:10.1109/tsmc.2016.2597240

Cited by 33 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several authors have underlined how automation can help forensic examiners [130,165,166,[175][176][177]. Examination and analysis techniques for time-function features and parameter features have been used in biometrics and can be transposed to forensic science [39,45,150,[178][179][180][181][182][183][184].…”

Section: Methodology In Dynamic Signature Examinationmentioning

confidence: 99%

Dynamic signatures: A review of dynamic feature variation and forensic methodology

Linden

Marquis

Bozza

et al. 2018

Forensic Science International

View full text Add to dashboard Cite

This article focuses on dynamic signatures and their features. It provides a detailed and critical review of dynamic feature variations and circumstantial parameters affecting dynamic signatures. The state of the art summarizes available knowledge, meant to assist the forensic practitioner in cases presenting extraordinary writing conditions. The studied parameters include hardware-related issues, aging and the influence of time, as well as physical and mental states of the writer. Some parameters, such as drug and alcohol abuse or medication, have very strong effects on handwriting and signature dynamics. Other conditions such as the writer's posture and fatigue have been found to affect feature variation less severely. The need for further research about the influence of these parameters, as well as handwriting dynamics in general is highlighted. These factors are relevant to the examiner in the assessment of the probative value of the reported features. Additionally, methodology for forensic examination of dynamic signatures is discussed. Available methodology and procedures are reviewed, while pointing out major technical and methodological advances in the field of forensic handwriting examination. The need for sharing the best practice manuals, standard operating procedures and methodologies to favor further progress is accentuated.

show abstract

Section: Methodology In Dynamic Signature Examinationmentioning

confidence: 99%

Dynamic signatures: A review of dynamic feature variation and forensic methodology

Linden

Marquis

Bozza

et al. 2018

Forensic Science International

View full text Add to dashboard Cite

show abstract

“…There exists in variety of approaches that transform higher dimensional data to lower dimension and speed up the upcoming processes. These include Fourier Transform [7,8], Discrete Wavelet Transform (DWT) [9,10,11], and Discrete Cosine Transform (DCT) [12,13]. Using DWT in feature extraction from handwritten digital signatures yielding superior verification rate in comparison to time domain verification system is found in [14].…”

Section: Introductionmentioning

confidence: 99%

“…However, system performance can further be improved by exploiting a different transformation. In [10], DWT is used to enhance the feature vectors in order to maximally separate genuine and forged signatures. More recently, Cpalka et al in [13] used the combination of DWT and DCT for signatures' local information extraction.…”

Section: Introductionmentioning

confidence: 99%

Online Signature Verification for Forgery Detection

Rizwan¹,

Aadil²,

Durrani³

et al. 2023

IJACSA

View full text Add to dashboard Cite

The increasing trend of using e-versions of document transmission and storage requires the electronic verification of sender/author. This research presents an efficient and robust online handwritten signature verification system targeting verification rates better than the available state-of-theart systems in the presence of skilled forgeries. Fourier analysis is employed on the signatures to represent feature vectors in higher dimensional space followed by Local Fisher Discriminant Analysis to obtain compress representation while enhancing inter-class scatter between signature patterns. Signature modeling is performed using m-mediod-based modeling approach where m-mediods are put on to represent data distribution in each class. Connected component labeling is applied to binarized images of Urdu text to extract ligatures which are separated into primary ligatures and diacritics. Fast Euclidean Distance is used as dis(similarity). A total of 2414 signature samples including skilled forgeries are considered in our study. The evaluation of the proposed system on Japanese signature dataset provided by SigWiComp2013 realized promising results than the competitors.

show abstract

“…Liu et al used Discrete Cosine Transform to obtain a set of signature feature vectors from signature time series data, and introduced a feature sparse representation strategy, which effectively reduced the computational complexity of signature verification 5 . Song et al uses the wavelet packet of the optimal mother wavelet to decompose the spectral information of signature features, and obtains the optimal feature subspace to verify the signature, which expands the research on signature feature extraction 6 .…”

Section: Introductionmentioning

confidence: 99%