SURDS: Self-Supervised Attention-guided Reconstruction and Dual Triplet Loss for Writer Independent Offline Signature Verification

Chattopadhyay, Soumitri; Manna, Siladittya; Bhattacharya, Sumanta; Pal, Umapada

doi:10.1109/icpr56361.2022.9956442

Cited by 15 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each individual has 24 genuine signatures and 30 forged signatures. We compare other methods, including IDN [17], CBCapsNet [23] and SURDS [24]. Tables 6 and 7 show the results of different methods on the two datasets, respectively, with the CBCapsNet [23] method on the BHSig-H dataset showing the highest accuracy of 100%.…”

Section: Comparison With the Classical Methodsmentioning

confidence: 99%

“…Wei P et al [17] proposed an Inverse Identification Network (IDN), which focuses on the characteristics of signature strokes. Recent work includes topological graphs [18], Siamese networks [19], deep metric learning for regions [20], RNN networks [21], graph neural network methods [22], models based on Capsule and CNN networks [23], and the encoder-decoder architecture approach [24]. By adopting deep learning methods, it can be widely applied in fields such as forensic identification and finance to improve the progress of issuing certifications and reduce work intensity.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FC-ResNet: A Multilingual Handwritten Signature Verification Model Using an Improved ResNet with CBAM

et al. 2023

View full text Add to dashboard Cite

Offline signature verification is a widely used biometric method in finance, law, and administrative procedures. However, existing deep convolutional neural network models perform poorly on signature datasets that span different regions and ethnic people, while also suffering from problems such as large parameter counts and slow inference speeds. To address these issues, we propose an improved residual network model (FC-ResNet). This model introduces a convolutional block attention module into the classical residual network to adapt to the diversity and variability of signatures, while also compressing the model for lightweight deployment. Due to the lack of public, offline handwritten signature datasets for ethnic people, we collected a large-scale offline handwritten signature dataset, including genuine signatures and forged signatures in Chinese, Uyghur, Kazakh, and Kirgiz, totaling 38,400 images. Our FC-ResNet model achieved an accuracy of over 96% for each language in our self-built dataset, as well as accuracy rates of 96.21%, 98.42%, and 97.28% on the public datasets CEDAR, BHSig-B, and BHSig-H, respectively. Based on the above experimental results, our proposed model demonstrates great potential for both public and self-built signature datasets, while also exhibiting significant advantages in lightweight model deployment. We believe that this work can provide a feasible solution for ethnic people signature verification.

show abstract

Section: Comparison With the Classical Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

FC-ResNet: A Multilingual Handwritten Signature Verification Model Using an Improved ResNet with CBAM

et al. 2023

View full text Add to dashboard Cite

show abstract

“…The present deep learning used in signature recognition is supervised learning, and the addition of self-supervised VOLUME XX, 2017 learning to the signature verification work proposed in [2] is also a relatively great inspiration for further research on signature recognition in the future. Self-supervised learning is a specific type of unsupervised learning that involves using labels found in the data itself to do supervised learning.…”

Section: C) Self-supervised Learningmentioning

confidence: 99%

“…In this work, there are two different concepts: verification [2] and recognition [3]. The former addresses the dichotomous problem and focuses primarily on determining whether a specific signature is real or fake.…”

Section: Introductionmentioning

confidence: 99%

“…However, it does not get important dynamic information. Because the sample lacks dynamic information that can identify handwriting activity, researchers must meticulously capture quite well data such as a signature's line and writing manner [2]. Currently, offline signatures can only seek specificity among them based on static information for instance shape, outline, and position, and then classify them for recognition [4]- [6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advances in Offline Handwritten Signature Recognition Research: A Review

Wang,

Muhammat,

Yadikar

et al. 2023

IEEE Access

View full text Add to dashboard Cite

A person's handwritten signature, one of the methods frequently used to confirm their identity, is used exclusively to confirm the biometric identification of different financial, legal, banking, insurance, and other business documents. Signature recognition techniques are used to identify which user someone's signature is affiliated with. In recent years, many researchers have worked on applying new methods to this work, and deep learning methods have become quite prevalent among them. In order to provide more researchers with a better comprehension of how offline handwritten signature recognition work has evolved, the existing approaches, different architectures, challenging issues, and trends within the last 15 years, this paper follows a protocol to organize this work, collects information primarily from studies published in four major databases, applies inclusion and exclusion criteria, reviews offline handwritten signature recognition methods, including issues such as feature extraction and classification, and attempts to summarize the challenges and opportunities in the field. This paper emphasizes the popularity of research directions in this research area in deep learning. In contrast to other surveys in the field, this paper is not limited to a particular phase of work but provides a detailed account of each stage with the expectation that this will help future researchers.INDEX TERMS Offline handwritten signature recognition; deep learning; traditional methods; biometric; review.

show abstract

DetailSemNet: Elevating Signature Verification Through Detail-Semantic Integration

Shih,

Huang,

Shih

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

SURDS: Self-Supervised Attention-guided Reconstruction and Dual Triplet Loss for Writer Independent Offline Signature Verification

Cited by 15 publications

References 19 publications

FC-ResNet: A Multilingual Handwritten Signature Verification Model Using an Improved ResNet with CBAM

FC-ResNet: A Multilingual Handwritten Signature Verification Model Using an Improved ResNet with CBAM

Advances in Offline Handwritten Signature Recognition Research: A Review

DetailSemNet: Elevating Signature Verification Through Detail-Semantic Integration

Contact Info

Product

Resources

About