Machine learning-based offline signature verification systems: A systematic review |
| |
| Affiliation: | 1. College of Information Science and Technology, Shihezi University, Shihezi, China;2. Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan;3. Department of Computing, National University of Sciences and Technology, Islamabad, Pakistan;4. German Research Center for Artificial Intelligence, Kaiserslautern, Germany;5. Graduate School of Engineering, Saitama Institute of Technology, Saitama, Japan;1. Machine Learning and Computational Modeling Lab, Control and Intelligent Processing Center of Excellence, School of Electrical and Computer Engineering, University of Tehran, Tehran, Iran;2. School of Cognitive Sciences, Institute for research in fundamental sciences, Tehran, Iran;1. Department of Informatics, DIVA Group, University of Fribourg, 1700 Fribourg, Switzerland;2. Luleå University of Technology, EISLAB Machine Learning, Luleå, 971 87, Sweden;3. Institute for Information Systems, University of Applied Sciences and Arts Northwestern Switzerland, Olten, 4600 Switzerland;4. Institute of Complex Systems, University of Applied Sciences and Arts Western Switzerland, Fribourg, 1700, Switzerland;1. Centro de Informática, Universidade Federal de Pernambuco, Recife (PE), Brazil;2. École de Technologie Supérieure - Université du Québec, Montreal, Québec, Canada;1. Telsip Laboratory, University of West Attica, Petrou Ralli 250 Ave. Egaleo, 12241, Greece;2. CNRS, laboratoire LJK, Université Grenoble-Alpes, France;3. Department of Physics, University of Patras, Rio, 26504, Greece |
| |
| Abstract: | The offline signatures are the most widely adopted biometric authentication techniques in banking systems, administrative and financial applications due to its simplicity and uniqueness. Several automated techniques have been developed to anticipate the genuineness of the offline signature. However, the recapitulate of the existing literature on machine learning-based offline signature verification (OfSV) systems are available in a few review studies only. The objective of this systematic review is to present the state-of-the-art machine learning-based models for OfSV systems using five aspects like datasets, preprocessing techniques, feature extraction methods, machine learning-based verification models and performance evaluation metrics. Thus, five research questions were identified and analysed in this context. This review covers the articles published between January 2014 and October 2019. A systematic approach has been adopted to select the 56 articles. This systematic review revealed that recently, the deep learning-based neural network attained the most promising results for the OfSV systems on public datasets. This review consolidates the state-of-the-art OfSV systems performances in selected studies on five public datasets (CEDAR, GPDS, MCYT-75, UTSig and BHSig260). Finally, fifteen open research issues were identified for future development. |
| |
| Keywords: | Offline signature verification Feature extraction Writer identification Deep convolutional neural network Handwriting recognition Signature forgery detection |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
