Writer independent offline signature verification based on asymmetric pixel relations and unrelated training-testing datasets

Zois, Elias N.; Alexandridis, Alex; Economou, George

doi:10.1016/j.eswa.2019.01.058

Cited by 50 publications

(26 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although these models presented the best results, they are writerdependent (WD); thus, our approach offers the advantage of being much more scalable, since only one classifier is used, while theirs requires 300. Compared to the other WI models, our approach was able to outperform almost them all, except the model proposed by Zois et al (2019a). It is worth noting that there is still room for improvement in our approach, such as, using ensemble or feature selection, which are approaches used in the paper by Zois et al (2019a).…”

Section: Methodsmentioning

confidence: 86%

“…Compared to the other WI models, our approach was able to outperform almost them all, except the model proposed by Zois et al (2019a). It is worth noting that there is still room for improvement in our approach, such as, using ensemble or feature selection, which are approaches used in the paper by Zois et al (2019a).…”

Section: Methodsmentioning

confidence: 86%

“…In the paper by Zois et al (2019a), the authors also used a transfer learning methodology. In this scenario, our approach obtains comparable results, being better in the MCYT dataset and worse when CEDAR and GPDS datasets are considered.…”

Section: Transfer Learningmentioning

confidence: 99%

“…In offline HSV, the signature is acquired after the writing process is completed, and the system deals with the signature as an image. For instance, credit card transactions or document authentication are among real-world applications using HSV systems (Hafemann et al, 2017b;Zois et al, 2019a).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A white-box analysis on the writer-independent dichotomy transformation applied to offline handwritten signature verification

Souza

Oliveira

Cruz

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

High number of writers, small number of training samples per writer with high intra-class variability and heavily imbalanced class distributions are among the challenges and difficulties of the offline Handwritten Signature Verification (HSV) problem. A good alternative to tackle these issues is to use a writerindependent (WI) framework. In WI systems, a single model is trained to perform signature verification for all writers from a dissimilarity space generated by the dichotomy transformation. Among the advantages of this framework is its scalability to deal with some of these challenges and its ease in managing new writers, and hence of being used in a transfer learning context. In this work, we present a white-box analysis of this approach highlighting how it handles the challenges, the dynamic selection of references through fusion function, and its application for transfer learning. All the analyses are carried out at the instance level using the instance hardness (IH) measure. The experimental results show that, using the IH analysis, we were able to characterize "good" and "bad" quality skilled forgeries as well as the frontier region between positive and negative samples. This enables futures investigations on methods for improving discrimination between genuine signatures and skilled forgeries by considering * Corresponding author

show abstract

Section: Methodsmentioning

confidence: 86%

Section: Methodsmentioning

confidence: 86%

Section: Transfer Learningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A white-box analysis on the writer-independent dichotomy transformation applied to offline handwritten signature verification

Souza

Oliveira

Cruz

et al. 2020

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…UTSig and PHBC respectively. Writer Independent offline signature verification is purposed in the work[10].In the work, features based on Asymmetric pixel relation is used. Four publically available dataset are used in the work.…”

mentioning

confidence: 99%

Offline Signature Recognition u sing Pretrained Convolution Neural Network Model

Kumari¹,

Rana²

2019

IJEAT

View full text Add to dashboard Cite

Offline Signature recognition plays an important role in Forensic issues. In this paper, we explore Signature Identification and Verification using features extracted from pretrained Convolution Neural Network model (Alex Net). All the experiments are performed on signatures from three dataset (SigComp2011) (Dutch, Chinese), SigWiComp2013 (Japanese) and SigWIcomp2015 (Italian). The result shows that features extracted from pretrained Deep Convolution neural network and SVM as classifier show better results than that of Decision Tree. The accuracy of more than 96% for Japanese, Italian, Dutch and Chinese Signatures is obtained with Deep Convolution neural network and SVM as classifier.

show abstract

Offline Signature Verification Using Textural Descriptors

Hadjadj

Gattal

Djeddi

et al. 2019

Pattern Recognition and Image Analysis

View full text Add to dashboard Cite

Writer independent offline signature verification based on asymmetric pixel relations and unrelated training-testing datasets

Cited by 50 publications

References 55 publications

A white-box analysis on the writer-independent dichotomy transformation applied to offline handwritten signature verification

A white-box analysis on the writer-independent dichotomy transformation applied to offline handwritten signature verification

Offline Signature Recognition u sing Pretrained Convolution Neural Network Model

Offline Signature Verification Using Textural Descriptors

Contact Info

Product

Resources

About