The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
La reconnaissance de chiffres manuscrits est une tâche classique et importante dans le domaine de la vision par ordinateur. Nous proposons deux nouveaux modèles d'apprentissage profond pour cette tâche, qui combinent la méthode d'extraction de bords et les structures de réseau siamois/triple. Nous évaluons les modèles sur sept ensembles de données numériques manuscrites et les résultats démontrent à la fois la simplicité et l'efficacité de nos modèles, par rapport aux méthodes de base.
Weiwei JIANG
Tsinghua University
Le ZHANG
Hubei University
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.
Copier
Weiwei JIANG, Le ZHANG, "Edge-SiamNet and Edge-TripleNet: New Deep Learning Models for Handwritten Numeral Recognition" in IEICE TRANSACTIONS on Information,
vol. E103-D, no. 3, pp. 720-723, March 2020, doi: 10.1587/transinf.2019EDL8199.
Abstract: Handwritten numeral recognition is a classical and important task in the computer vision area. We propose two novel deep learning models for this task, which combine the edge extraction method and Siamese/Triple network structures. We evaluate the models on seven handwritten numeral datasets and the results demonstrate both the simplicity and effectiveness of our models, comparing to baseline methods.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8199/_p
Copier
@ARTICLE{e103-d_3_720,
author={Weiwei JIANG, Le ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Edge-SiamNet and Edge-TripleNet: New Deep Learning Models for Handwritten Numeral Recognition},
year={2020},
volume={E103-D},
number={3},
pages={720-723},
abstract={Handwritten numeral recognition is a classical and important task in the computer vision area. We propose two novel deep learning models for this task, which combine the edge extraction method and Siamese/Triple network structures. We evaluate the models on seven handwritten numeral datasets and the results demonstrate both the simplicity and effectiveness of our models, comparing to baseline methods.},
keywords={},
doi={10.1587/transinf.2019EDL8199},
ISSN={1745-1361},
month={March},}
Copier
TY - JOUR
TI - Edge-SiamNet and Edge-TripleNet: New Deep Learning Models for Handwritten Numeral Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 720
EP - 723
AU - Weiwei JIANG
AU - Le ZHANG
PY - 2020
DO - 10.1587/transinf.2019EDL8199
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E103-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2020
AB - Handwritten numeral recognition is a classical and important task in the computer vision area. We propose two novel deep learning models for this task, which combine the edge extraction method and Siamese/Triple network structures. We evaluate the models on seven handwritten numeral datasets and the results demonstrate both the simplicity and effectiveness of our models, comparing to baseline methods.
ER -