Forgery-free signature verification with stroke-aware cycle-consistent generative adversarial network

Subscripto multiplex: A Riemannian symmetric positive definite strategy for offline signature verification

“…and reported more and more often, which provide synthetic signatures by duplicating real signature images [13,[57][58][59]. Another recent work [24] proposes a convolutional neural network model for offline HSV, called SigCNN, and utilize CycleGAN in style transfer fields to generate realistic offline signatures from online specimens and their duplicates. Also Maruyama et al in [13] have proposed a duplicate feature generation process with notable results.…”

“…image) [8][9][10][11][12][13]. An alternative classification of offline signature verification methodologies divides them into a) handcrafted methods, which mainly utilize image processing and computer vision techniques and b) data-driven or learningbased approaches with typical representatives Bags of Visual Words [14,15] sparse representation [11] and deep learning methodologies [8,12,[16][17][18][19][20][21][22][23][24][25][26]. The latter, address the problem by utilizing either classification [19,27,28] or metric learning [20,21,29] losses trained only with genuine samples [20,30], or even along with skilled forgeries [12,29].…”

“…In order to address the notorious limited training data curse of pattern recognition, especially in offline signature verification [13,24] we propose two methods for feature points augmentation or duplicates. To be specific, we propose two methods for the creation of duplicate covariance matrices when only a few (e.g.…”

DarkNet19 and multiple feature selectors based deep feature engineering model for fake signature detection

“…When tested on the CEDAR dataset, the methods achieved accuracy rates of 99.24% and 98.79%. Jiang and his team's study [3], introduces a new method for handwritten signature verification. Using online signatures, they developed a Convolutional Neural Network (CNN) called SigCNN to generate offline signatures.…”

One vs. One Offline Signature Verification: A Forensic Handwriting Examiners Perspective

“…Nevertheless, performance is not the only attribute for signature verification systems. In addition to the seven features identified by Jain for biometric systems [33] and other pertinent aspects like security, fairness, and privacy [34], explainability has emerged as a crucial factor for the practical implementation of these systems [5]. The lack of explanation in the functioning of these systems prevents their use in some practical contexts, such as finance, healthcare, government, commercial transactions, and security.…”