The DOI matches its Crossref record; 8 of the 8 references it cites were found in a registry or an index.
SIGNATURE VERIFICATION USING A “SIAMESE” TIME DELAY NEURAL NETWORK
Abstract
This paper describes an algorithm for verification of signatures written on a pen-input tablet. The algorithm is based on a novel, artificial neural network, called a "Siamese" neural network. This network consists of two identical sub-networks joined at their outputs. During training the two sub-networks extract features from two signatures, while the joining neuron measures the distance between the two feature vectors. Verification consists of comparing an extracted feature vector with a stored feature vector for the signer. Signatures closer to this stored representation than a chosen threshold are excepted, all other signatures are rejected as forgeries.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Most of the image registration methods using deep learning are based on a Siamese network (Bromley et al., 1994;Merkle et al., 2017;He et al., 2018;Hughes et al., 2018a;Wang et al., 2018b).”
From Deep learning in remote sensing applications: A meta-analysis and review (2019) · cites this paper as Bromley et al., 1994
Citations
Cites
(1973) · CERN Document Server (European Organization for Nuclear Research) · Cited by 12,895
Generalization and network design strategies
LeCun, Y. (1989) · Cited by 885
Self-citationNeural Networks for Fingerprint Recognition
Baldi, P., & Chauvin, Y. (1993) · Neural Computation · doi:10.1162/neco.1993.5.3.402 · Cited by 171
Automatic Signature Verification Based on Accelerometry
Herbst, N. M., & Liu, C. N. (1977) · IBM Journal of Research and Development · doi:10.1147/rd.213.0245 · Cited by 108
A time delay neural network architecture for speech recognition
Lang, K. (1989) · Cited by 76
Signature verification from position, velocity and acceleration signals: a comparative study
Réjean Plamondon, B., & Parizeau, M. (2003) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr.1988.28218 · Cited by 54
DYNAMIC APPROACHES TO HANDWRITTEN SIGNATURE VERIFICATION
Lorette, G., & Réjean Plamondon, B. (1990) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789814439329_0002 · Cited by 26
A time delay neural network character recognizer for a touch terminal
Guyon, I., Albrecht, P., LeCun, Y., et al. (1990) · Cited by 8
Self-citation
Cited by
Sorted by citations
Items 1,001–1,003 of 1,003
Never Give Up: Learning Directed Exploration Strategies
Badia, A. P., Sprechmann, P., Vitvitskyi, A., Guo, D., Piot, B., Kapturowski, S., Tieleman, O., Arjovsky, M., Pritzel, A., Bolt, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2002.06038 · Cited by 170
Chung, Y.-A., & Weng, W.-H. (2017) · arXiv · doi:10.48550/arxiv.1711.08490 · Cited by 58
Provable Guarantees for Self-Supervised Deep Learning with Spectral Contrastive Loss
HaoChen, J. Z., Wei, C., Gaidon, A., & Ma, T. (2021) · arXiv · doi:10.48550/arxiv.2106.04156 · Cited by 53
Metadata
- Authors
- BROMLEY, J., BENTZ, J. W., BOTTOU, L., GUYON, I., LECUN, Y., MOORE, C., SÄCKINGER, E., & SHAH, R.
- Affiliations
- AT&T (United States) (US)
- Venue
- Series in Machine Perception and Artificial Intelligence
- Publisher
- WORLD SCIENTIFIC
- Published
- 1994-01
- Pages
- 25-44
- ISSN
- 1793-0839 (ISSN-L)
- OpenAlex
- W2127589108
- Cited by
- 2,350
- References
- 8
- Citations by year
- 2026: 47 · 2025: 148 · 2024: 177 · 2023: 218 · 2022: 212 · 2021: 350 · 2020: 409 · 2019: 339 · 2018: 194 · 2017: 100 · 2016: 68 · 2015: 36 · 2014: 8 · 2013: 4 · 2012: 6
- FWCI
- 0.85
- Type
- book chapter
- Language
- en
- Open access
- closed
- Locations
- Series in machine perception and artificial intelligence (publishedVersion)
- Open Research Online (The Open University) (acceptedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Handwritten Text Recognition Techniques
- Physical Sciences › Computer Science › Information Systems › User Authentication and Security Systems
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Keywords
- signature verification, Siamese network, time-delay neural networks, feature extraction, forgery detection, biometric authentication
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
