What is it about?
Reduced training sets is a major problem typically found on the task of offline signature verification. In order to increase the number of samples, the use of synthetic signatures can be taken into account. In this work, a new method for the generation of synthetic offline signatures by using dynamic and static (real) ones is presented. The synthesis is here faced under the perspective of supervised training: the learning model is trained to perform the task of online to offline signature conversion. The approach is based on a Deep Convolutional Neural Network. The main goal is to enlarge offline training dataset in order to improve the performance of the offline signature verification systems.
Featured Image
Why is it important?
The use of synthetic samples (in the training phase) generated with the proposed method on a state-of-the-art classification system exhibits performance similar to those obtained using real signatures, moreover the combination of real and synthetic signature in the training set is also able to show improvements of the signature verification specially in case of the skilled forgeries.
Perspectives
This article is really special since through this work we consolidate a fruitful partnership with brilliant researchers in the handwritten signature area from Università degli Studi di Bari, my dear friends Prof. Giuseppe Pirlo, and Prof. Donato Impedovo. In fact, this is just the beginning of this long-term collaboration between our research groups.
BYRON BEZERRA
Universidade de Pernambuco
Read the Original
This page is a summary of: A Deep Learning Approach to Generate Offline Handwritten Signatures Based on Online Samples, IET Biometrics, December 2018, the Institution of Engineering and Technology (the IET),
DOI: 10.1049/iet-bmt.2018.5091.
You can read the full text:
Contributors
The following have contributed to this page
