A Hierarchical Classification Method for US Bank-Notes
Summary :
This paper describes a method for the classification of bank-notes. The algorithm has three stages, and classifies bank-notes with very low error rates and at high speeds. To achieve the very low error rates, the result of classification is checked in the final stage by using different features to those used in the first two. High-speed processing is mainly achieved by the hierarchical structure, which leads to low computational costs. In evaluation on 32,850 samples of US bank-notes, with the same number used for training, the algorithm classified all samples precisely with no error sample. We estimate that the worst error rate is 3.1E-9 for the classification statistically.
- Publication
- IEICE TRANSACTIONS on Information Vol.E89-D No.7 pp.2061-2067
- Publication Date
- 2006/07/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1093/ietisy/e89-d.7.2061
- Type of Manuscript
- Special Section PAPER (Special Section on Machine Vision Applications)
- Category
- Pattern Discrimination and Classification
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Tatsuhiko KAGEHIRO, Hiroto NAGAYOSHI, Hiroshi SAKO, "A Hierarchical Classification Method for US Bank-Notes" in IEICE TRANSACTIONS on Information,
vol. E89-D, no. 7, pp. 2061-2067, July 2006, doi: 10.1093/ietisy/e89-d.7.2061.
Abstract: This paper describes a method for the classification of bank-notes. The algorithm has three stages, and classifies bank-notes with very low error rates and at high speeds. To achieve the very low error rates, the result of classification is checked in the final stage by using different features to those used in the first two. High-speed processing is mainly achieved by the hierarchical structure, which leads to low computational costs. In evaluation on 32,850 samples of US bank-notes, with the same number used for training, the algorithm classified all samples precisely with no error sample. We estimate that the worst error rate is 3.1E-9 for the classification statistically.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e89-d.7.2061/_p
Copy
@ARTICLE{e89-d_7_2061,
author={Tatsuhiko KAGEHIRO, Hiroto NAGAYOSHI, Hiroshi SAKO, },
journal={IEICE TRANSACTIONS on Information},
title={A Hierarchical Classification Method for US Bank-Notes},
year={2006},
volume={E89-D},
number={7},
pages={2061-2067},
abstract={This paper describes a method for the classification of bank-notes. The algorithm has three stages, and classifies bank-notes with very low error rates and at high speeds. To achieve the very low error rates, the result of classification is checked in the final stage by using different features to those used in the first two. High-speed processing is mainly achieved by the hierarchical structure, which leads to low computational costs. In evaluation on 32,850 samples of US bank-notes, with the same number used for training, the algorithm classified all samples precisely with no error sample. We estimate that the worst error rate is 3.1E-9 for the classification statistically.},
keywords={},
doi={10.1093/ietisy/e89-d.7.2061},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - A Hierarchical Classification Method for US Bank-Notes
T2 - IEICE TRANSACTIONS on Information
SP - 2061
EP - 2067
AU - Tatsuhiko KAGEHIRO
AU - Hiroto NAGAYOSHI
AU - Hiroshi SAKO
PY - 2006
DO - 10.1093/ietisy/e89-d.7.2061
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E89-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2006
AB - This paper describes a method for the classification of bank-notes. The algorithm has three stages, and classifies bank-notes with very low error rates and at high speeds. To achieve the very low error rates, the result of classification is checked in the final stage by using different features to those used in the first two. High-speed processing is mainly achieved by the hierarchical structure, which leads to low computational costs. In evaluation on 32,850 samples of US bank-notes, with the same number used for training, the algorithm classified all samples precisely with no error sample. We estimate that the worst error rate is 3.1E-9 for the classification statistically.
ER -
English
