Combination of Convolutional Neural Network Architecture and its Learning Method for Rotation-Invariant Handwritten Digit Recognition

被引：4

作者：

Urazoe, Kazuya ^{[1
]}

Kuroki, Nobutaka ^{[1
]}

Hirose, Tetsuya ^{[2
]}

Numa, Masahiro ^{[1
]}

机构：

[1] Kobe Univ, Dept Elect & Elect Engn, Nada Ku, 1-1 Rokkodai Cho, Kobe, Hyogo 6578501, Japan

[2] Osaka Univ, Div Elect Elect & Informat Engn, 2-1 Yamadaoka, Suita, Osaka 5650871, Japan

来源：

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING | 2021年 / 16卷 / 01期

关键词：

handwritten digit recognition; convolutional neural network; rotation invariance; data augmentation; MNIST;

D O I：

10.1002/tee.23278

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

This letter presents several combinations of a convolutional neural network (CNN) and its learning method for rotation-invariant digit recognition. Rotation data augmentation is widely used for improving rotation invariance. Data augmentation commonly assigns the same label to all augmented images of the same source. However, this learning method causes some collisions between original and rotated digits. Thus, this letter presents three types of rotation-invariance learning methods and applies them to five popular CNN architectures. Experimental results indicate that multi-task learning on ResNet-50 is the best combination. (c) 2020 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

引用

页码：161 / 163

页数：3

共 50 条

[31] Character string recognition on maps, a rotation-invariant recognition method
Deseilligny, MP
LeMen, H
Stamon, G
PATTERN RECOGNITION LETTERS, 1995, 16 (12) : 1297 - 1310
[32] Rotation-invariant neural pattern recognition system estimating a rotation angle
Fukumi, M
Omatu, S
Nishikawa, Y
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1997, 8 (03): : 568 - 581
[33] Residual Neural Network Vs Local Binary Convolutional Neural Networks for Bilingual Handwritten Digit Recognition
Al-wajih, Ebrahim
Ghazali, Rozaida
Hassim, Yana Mazwin Mohmad
RECENT ADVANCES ON SOFT COMPUTING AND DATA MINING (SCDM 2020), 2020, 978 : 25 - 34
[34] A modal learning adaptive function neural network applied to handwritten digit recognition
Kang, Miao
Palmer-Brown, Dominic
INFORMATION SCIENCES, 2008, 178 (20) : 3802 - 3812
[35] Handwritten Digit Recognition with Neural Network<bold> </bold>
Malla, Satyanarayana, V
Sharma, Hitesh Kumar
Choudhury, Tanupriya
MICRO-ELECTRONICS AND TELECOMMUNICATION ENGINEERING, ICMETE 2021, 2022, 373 : 525 - 532
[36] Handwritten Digit Recognition Based on Depth Neural Network
Hou, Yawei
Zhao, Huailin
2017 2ND INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATICS AND BIOMEDICAL SCIENCES (ICIIBMS), 2017, : 35 - 38
[37] Very Deep Neural Network for Handwritten Digit Recognition
Li, Yang
Li, Hang
Xu, Yulong
Wang, Jiabao
Zhang, Yafei
INTELLIGENT DATA ENGINEERING AND AUTOMATED LEARNING - IDEAL 2016, 2016, 9937 : 174 - 182
[38] A Novel Deep Convolutional Neural Network Architecture Based on Transfer Learning for Handwritten Urdu Character Recognition
Oziuddeen, Mohammed Aarif Kilvisharam
Poruran, Sivakumar
Caffiyar, Mohamed Yousuff
TEHNICKI VJESNIK-TECHNICAL GAZETTE, 2020, 27 (04): : 1160 - 1165
[39] Performance analysis of hybrid deep learning framework using a vision transformer and convolutional neural network for handwritten digit recognition
Agrawal, Vanita
Jagtap, Jayant
Patil, Shruti
Kotecha, Ketan
METHODSX, 2024, 12
[40] A Novel Deep Convolutional Neural Network Structure for Off-line Handwritten Digit Recognition
Wen, Yan
Shao, Yi
Zheng, Dabo
PROCEEDINGS OF 2019 2ND INTERNATIONAL CONFERENCE ON BIG DATA TECHNOLOGIES (ICBDT 2019), 2019, : 216 - 220

← 1 2 3 4 5 →