Deep learning-based data augmentation method and signature verification system for offline handwritten signature
- PDF / 1,784,721 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 14 Downloads / 264 Views
THEORETICAL ADVANCES
Deep learning‑based data augmentation method and signature verification system for offline handwritten signature Muhammed Mutlu Yapıcı1 · Adem Tekerek2 · Nurettin Topaloğlu3 Received: 2 January 2020 / Accepted: 5 September 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Offline handwritten signature verification is a challenging pattern recognition task. One of the most significant limitations of the handwritten signature verification problem is inadequate data for training phases. Due to this limitation, deep learning methods that have obtained the state-of-the-art results in many areas achieve quite unsuccessful results when applied to signature verification. In this study, a new use of Cycle-GAN is proposed as a data augmentation method to address the inadequate data problem on signature verification. We also propose a novel signature verification system based on Caps-Net. The proposed data augmentation method is tested on four different convolutional neural network (CNN) methods, VGG16, VGG19, ResNet50, and DenseNet121, which are widely used in the literature. The method has provided a significant contribution to all mentioned CNN methods’ success. The proposed data augmentation method has the best effect on the DenseNet121. We also tested our data augmentation method with the proposed signature verification system on two widely used databases: GPDS and MCYT. Compared to other studies, our verification system achieved the state-of-the-art results on MCYT database, while it reached the second-best verification result on GPDS. Keywords Deep learning · Data augmentation · Signature verification · Convolutional neural networks
1 Introduction Biometric methods are the most widely used authentication methods. Although there are many biometric authentication methods, the handwritten signature is still the most widely used one even in the modern world. Therefore, it is important to ensure the reliability of the signatures by distinguishing genuine and forged signatures. This makes the signature verification problem one of the extensive research fields. The most important problem of offline signature verification systems is high intra-personal variability. Even the same writer cannot sign the same signature in the second time using the same method [28]. This obstacle distinguishes handwritten signatures from other biometric methods and * Muhammed Mutlu Yapıcı [email protected] 1
Computer Technologies Department, Ankara University, Ankara, Turkey
2
Information Technology Department, Gazi University, Ankara, Turkey
3
Computer Engineering Faculty, Technology Faculty, Gazi University, Ankara, Turkey
makes it a difficult problem to solve. To tackle this challenging problem, signature competitions named as SigComp2011 [33], 4NSigComp2012 [34] and SigWiComp2013 [39] were organized. On the other hand, researches in this field have resulted in numerous verification methods based on support vector machines (SVM) [29], dynamic time wrap (DTW) [7], principl
Data Loading...
