Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics
Systems based on deep neural networks have made a breakthrough in many different pattern recognition tasks. However, the use of these systems with traditional architectures seems not to work properly when the amount of training data is scarce. This is the case of the on-line signature verification t...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2018-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8259229/ |
| _version_ | 1818410542510899200 |
|---|---|
| author | Ruben Tolosana Ruben Vera-Rodriguez Julian Fierrez Javier Ortega-Garcia |
| author_facet | Ruben Tolosana Ruben Vera-Rodriguez Julian Fierrez Javier Ortega-Garcia |
| author_sort | Ruben Tolosana |
| collection | DOAJ |
| description | Systems based on deep neural networks have made a breakthrough in many different pattern recognition tasks. However, the use of these systems with traditional architectures seems not to work properly when the amount of training data is scarce. This is the case of the on-line signature verification task. In this paper, we propose a novel writer-independent on-line signature verification systems based on Recurrent Neural Networks (RNNs) with a Siamese architecture whose goal is to learn a dissimilarity metric from the pairs of signatures. To the best of our knowledge, this is the first time these recurrent Siamese networks are applied to the field of on-line signature verification, which provides our main motivation. We propose both Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) systems with a Siamese architecture. In addition, a bidirectional scheme (which is able to access both past and future context) is considered for both LSTMand GRU-based systems. An exhaustive analysis of the system performance and also the time consumed during the training process for each recurrent Siamese network is carried out in order to compare the advantages and disadvantages for practical applications. For the experimental work, we use the BiosecurID database comprised of 400 users who contributed a total of 11,200 signatures in four separated acquisition sessions. Results achieved using our proposed recurrent Siamese networks have outperformed the state-of-the-art on-line signature verification systems using the same database. |
| first_indexed | 2024-12-14T10:17:11Z |
| format | Article |
| id | doaj.art-1af8e257d010420d90b646ab8e9559f2 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T10:17:11Z |
| publishDate | 2018-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1af8e257d010420d90b646ab8e9559f22022-12-21T23:06:44ZengIEEEIEEE Access2169-35362018-01-0165128513810.1109/ACCESS.2018.27939668259229Exploring Recurrent Neural Networks for On-Line Handwritten Signature BiometricsRuben Tolosana0https://orcid.org/0000-0002-9393-3066Ruben Vera-Rodriguez1Julian Fierrez2Javier Ortega-Garcia3Biometrics and Data Pattern Analytics (BiDA) Lab-ATVS, Universidad Autonoma de Madrid, Madrid, SpainBiometrics and Data Pattern Analytics (BiDA) Lab-ATVS, Universidad Autonoma de Madrid, Madrid, SpainBiometrics and Data Pattern Analytics (BiDA) Lab-ATVS, Universidad Autonoma de Madrid, Madrid, SpainBiometrics and Data Pattern Analytics (BiDA) Lab-ATVS, Universidad Autonoma de Madrid, Madrid, SpainSystems based on deep neural networks have made a breakthrough in many different pattern recognition tasks. However, the use of these systems with traditional architectures seems not to work properly when the amount of training data is scarce. This is the case of the on-line signature verification task. In this paper, we propose a novel writer-independent on-line signature verification systems based on Recurrent Neural Networks (RNNs) with a Siamese architecture whose goal is to learn a dissimilarity metric from the pairs of signatures. To the best of our knowledge, this is the first time these recurrent Siamese networks are applied to the field of on-line signature verification, which provides our main motivation. We propose both Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) systems with a Siamese architecture. In addition, a bidirectional scheme (which is able to access both past and future context) is considered for both LSTMand GRU-based systems. An exhaustive analysis of the system performance and also the time consumed during the training process for each recurrent Siamese network is carried out in order to compare the advantages and disadvantages for practical applications. For the experimental work, we use the BiosecurID database comprised of 400 users who contributed a total of 11,200 signatures in four separated acquisition sessions. Results achieved using our proposed recurrent Siamese networks have outperformed the state-of-the-art on-line signature verification systems using the same database.https://ieeexplore.ieee.org/document/8259229/Biometricsdeep learningon-line handwritten signature verificationrecurrent neural networksLSTMGRU |
| spellingShingle | Ruben Tolosana Ruben Vera-Rodriguez Julian Fierrez Javier Ortega-Garcia Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics IEEE Access Biometrics deep learning on-line handwritten signature verification recurrent neural networks LSTM GRU |
| title | Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics |
| title_full | Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics |
| title_fullStr | Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics |
| title_full_unstemmed | Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics |
| title_short | Exploring Recurrent Neural Networks for On-Line Handwritten Signature Biometrics |
| title_sort | exploring recurrent neural networks for on line handwritten signature biometrics |
| topic | Biometrics deep learning on-line handwritten signature verification recurrent neural networks LSTM GRU |
| url | https://ieeexplore.ieee.org/document/8259229/ |
| work_keys_str_mv | AT rubentolosana exploringrecurrentneuralnetworksforonlinehandwrittensignaturebiometrics AT rubenverarodriguez exploringrecurrentneuralnetworksforonlinehandwrittensignaturebiometrics AT julianfierrez exploringrecurrentneuralnetworksforonlinehandwrittensignaturebiometrics AT javierortegagarcia exploringrecurrentneuralnetworksforonlinehandwrittensignaturebiometrics |