Siamese Network for Learning Genuine and Forged Offline Signature Verification

Jagtap, Amruta B.; Sawat, Dattatray D.; Hegadi, Ravindra S.; Hegadi, Rajendra

doi:10.1007/978-981-13-9187-3_12

Cited by 9 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Siamese networks can be defined as two identical sub-networks with the same weights used to learn a feature space with similar observations clustered together. This was accomplished by revealing the network to a similar and dissimilar pair of statements and reducing the Euclidean distance between the identical pairs while increasing it between different pairs [22]. In 2019, Ramesh Kumar Mohapatra et al developed a method for learning characteristics from pre-processed authentic and forging signatures using convolutional neural networks (CNNs).…”

Section: Related Workmentioning

confidence: 99%

Siamese Convolutional Neural Network-Based Twin Structure Model for Independent Offline Signature Verification

et al. 2022

View full text Add to dashboard Cite

One of the toughest biometrics and document forensics problems is confirming a signature's authenticity and legal identity. A forgery may vary from a genuine signature by specific distortions. Therefore, it is necessary to continuously monitor crucial distinctions between real and forged signatures for secure work and economic growth, but this is particularly difficult in writer-independent tasks. We thus propose an innovative and sustainable writer-independent approach based on a Siamese neural network for offline signature verification. The Siamese network is a twin-like structure with shared weights and parameters. Similar and dissimilar images are exposed to this network, and the Euclidean distances between them are calculated. The distance is reduced for identical signatures, and the distance is increased for different signatures. Three datasets, namely GPDS, BHsig260 Hindi, and BHsig260 Bengali datasets, were tested in this work. The proposed model was analyzed by comparing the results of different parameters such as optimizers, batch size, and the number of epochs on all three datasets. The proposed Siamese neural network outperforms the GPDS synthetic dataset in the English language, with an accuracy of 92%. It also performs well for the Hindi and Bengali datasets while considering skilled forgeries.

show abstract

Section: Related Workmentioning

confidence: 99%

Siamese Convolutional Neural Network-Based Twin Structure Model for Independent Offline Signature Verification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In the work of [5], they developed an application on offline signature verification by establishing the Siamese Network, in which the Convolutional Neural Network used as a subnet. In the Siamese network, they aimed to make the real-fake signature distinction more accurately by adding some statistical features to the embedding vector, which is the mathematical expression of each signature image.…”

Section: Related Workmentioning

confidence: 99%

Siamese Sinir Ağı One-Shot Öğrenmeyi Kullanarak İmza Doğrulama

Arısoy

2021

International Journal of Engineering and Innovative Research

View full text Add to dashboard Cite

With the acceleration of digitalization in all areas of our lives, the need for biometric verification methods is increasing. The fact that biometric data is unique and biometric verification is stronger against phishing attacks compared to password-based authentication methods, has increased its preference rate. Signature verification, which is one of the biometric verification types, plays an important role in many areas such as banking systems, administrative and judicial applications. There are 2 types of signature verification, online and offline, for identifying the identity of the person and detecting signature forgery. Online signature verification is carried out during signing and temporal dynamic data are available regarding the person's signature. Offline verification is applied by scanning the image after signing, and this verification is limited to spatial data. Therefore, the offline signature verification process is considered a more challenging task.In this study, offline signature verification, independent of the writer, based on One-Shot Learning, was performed using Siamese Neural Network. Due to the fact that the Deep Convolution Neural Network requires a large amount of labeled data for image classification, real and fake signature distinction has been achieved by using the One-Shot Learning method, which can perform a successful classification by using less numbers of signature images. As a result of the experiments conducted on signature datasets, using the Siamese architecture, the proposed approach achieved percentage accuracy of 93.23, 90.11, 89.99, 92.35 verification in 4NSigComp2012, SigComp2011, 4NSigComp2010 and BHsig260 respectively.

show abstract