Automatic Signature Verifier Using Gaussian Gated Recurrent Unit Neural Network

Table 6

Performance comparison of proposed 2GRUNN with other existing methods and CEDAR dataset.

Paper title	Author	Technique	Performance metrics
From text to signatures: knowledge transfer for efficient deep feature learning in offline signature verification [31]	Dimitrios Tsourounis, Ilias Theodorakopoulos, Elias N. Zois, George Economou	CNN	EER = 2.5
Offline signature verification using a region based deep metric learning network [26]	Li Liu, Linlin Huang, Fei Yin, Youbin Chen	Deep convolutional siamese network	EER = 6.67
CBCapsNet: a novel writer-independent offline signature verification model using a CNN-based architecture and capsule neural networks [27]	Ebrahim Parcham, Mahdi Ilbeygi, Mohammad Amini	A combination of CNN and CapsNet	FAR = 9.45 and FRR = 8.81 for CBCapsNet
Learning the micro deformations by max-pooling for offline signature verification [30]	Yuchen Zheng, Brian Kenji Iwana, Muhammad Imran Malik,Sheraz Ahmed,Wataru Ohyama, Seiichi Uchida	CNN	EER for random forgery = 1.78 and for skilled forgery = 33.82
Proposed network		Gaussian gated recurrent unit neural network	FAR = 1.82; FRR = 3.03; EER = 2.4