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
收藏
页码：161 / 163
页数：3
相关论文
共 50 条
  • [41] Learning Rotation-Invariant Representations of Point Clouds Using Aligned Edge Convolutional Neural Networks
    Zhang, Junming
    Yu, Ming-Yuan
    Vasudevan, Ram
    Johnson-Roberson, Matthew
    2020 INTERNATIONAL CONFERENCE ON 3D VISION (3DV 2020), 2020, : 200 - 209
  • [42] Rotation-Invariant Wafer Map Pattern Classification With Convolutional Neural Networks
    Kang, Seokho
    IEEE ACCESS, 2020, 8 (08): : 170650 - 170658
  • [43] Multiscale Rotation-Invariant Convolutional Neural Networks for Lung Texture Classification
    Wang, Qiangchang
    Zheng, Yuanjie
    Yang, Gongping
    Jin, Weidong
    Chen, Xinjian
    Yin, Yilong
    IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, 2018, 22 (01) : 184 - 195
  • [44] Improved Handwritten Digit Recognition Using Convolutional Neural Networks (CNN)
    Ahlawat, Savita
    Choudhary, Amit
    Nayyar, Anand
    Singh, Saurabh
    Yoon, Byungun
    SENSORS, 2020, 20 (12) : 1 - 18
  • [45] Persian Handwritten Digit Recognition by Random Forest and Convolutional Neural Networks
    Zamani, Yasin
    Souri, Yaser
    Rashidi, Hossein
    Kasaei, Shohreh
    2015 9TH IRANIAN CONFERENCE ON MACHINE VISION AND IMAGE PROCESSING (MVIP), 2015, : 37 - 40
  • [46] Handwritten Digit Recognition of MNIST dataset using Deep Learning state-of-the-art Artificial Neural Network (ANN) and Convolutional Neural Network (CNN)
    Beohar, Drishti
    Rasool, Akhtar
    2021 INTERNATIONAL CONFERENCE ON EMERGING SMART COMPUTING AND INFORMATICS (ESCI), 2021, : 542 - 548
  • [47] ROTATION-INVARIANT NEURAL PATTERN-RECOGNITION SYSTEM WITH APPLICATION TO COIN RECOGNITION
    FUKUMI, M
    OMATU, S
    TAKEDA, F
    KOSAKA, T
    IEEE TRANSACTIONS ON NEURAL NETWORKS, 1992, 3 (02): : 272 - 279
  • [48] Spiking neural networks for handwritten digit recognition-Supervised learning and network optimization
    Kulkarni, Shruti R.
    Rajendran, Bipin
    NEURAL NETWORKS, 2018, 103 : 118 - 127
  • [49] COMPUTATIONALLY EFFICIENT SERIAL COMBINATION OF ROTATION-INVARIANT AND ROTATION COMPENSATING IRIS RECOGNITION ALGORITHMS
    Konrad, Mario
    Stoegner, Herbert
    Uhl, Andreas
    Wild, Peter
    VISAPP 2010: PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON COMPUTER VISION THEORY AND APPLICATIONS, VOL 1, 2010, : 85 - 90
  • [50] Handwritten Digit Recognition with Pattern Transformations and Neural Network Averaging
    Manuel Alonso-Weber, Juan
    Paz Sesmero, M.
    Gutierrez, German
    Ledezma, Agapito
    Sanchis, Araceli
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2013, 2013, 8131 : 335 - 342
12345