More Web Proxy on the site http://driver.im/

research-article

Hybrid CNN-GRU model for high efficient handwritten digit recognition

Authors:

Vantruong Nguyen,

Jie ChuAuthors Info & Claims

AIPR '19: Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition

Pages 66 - 71

https://doi.org/10.1145/3357254.3357276

Published: 16 August 2019 Publication History

Abstract

Recognition of handwritten digits is a challenging research topic in Optical Character Recognition (OCR) in recent years. In this paper, a hybrid model combining convolutional neural network (CNN) and gate recurrent units (GRU) is proposed, in which GRU is used to replace the CNN fully connected layer part to achieve high recognition accuracy with lower running time. In this model, the features of the original image are firstly extracted by the CNN, and then they are dynamically classified by the GRU. Experiment performed on MNIST handwritten digit dataset suggests that the recognition accuracy of 99.21% while the training time and testing time is only 57.91s and 3.54s, respectively.

References

[1]

Vajda, S., Santosh, K. C. 2016. A fast k-nearest neighbor classifier using unsupervised clustering. Handbook of Recent Trends in Image Processing and Pattern Recognition (RTIP2R). 709 (Dec. 2016), 185--193.

[2]

Babu, U. R., Venkateswarlu, Y., and Chintha, A. K. 2014. Handwritten digit recognition using K-nearest neighbour classifier. In World Congress on Computing and Communication Technologies, Trichirappalli, India, April 2014, 60--65.

[3]

Makkar, T., Kumar, Y., Dubey, A. K., Rocha Á. 2017. Analogizing time complexity of KNN and CNN in recognizing handwritten digits. In International Conference on Image Information Processing (ICIIP), Shimla, India (Dec. 2017), 1--6.

[4]

Lu, W. 2017. Handwritten digits recognition using PCA of histogram of oriented gradient. In IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM), Victoria, BC, Canada, (Aug. 2017).

[5]

Ebrahimzadeh, R., Jampour, M. 2014. Efficient handwritten digit recognition based on histogram of oriented gradients and SVM. International Journal of Computer Applications. 104, 9 (October 2014), 10--13.

[6]

Drewnik, M., Winiarski, Z. P. 2017. SVM Kernel Configuration and Optimization for the Handwritten Digit Recognition. Computer Information Systems and Industrial Management (CISIM). 10244 (June 2017), 87--98.

[7]

Khan, H. A. 2017. MCS HOG features and SVM based handwritten digit recognition system. Journal of Intelligent Learning Systems and Applications. 9, 2 (2017), 21--33.

[8]

Lauer, F., Suen, C. Y., and Bloch, G. 2007. A trainable feature extractor for handwritten digit recognition. Pattern Recognition. 40, 6 (June 2007), 1816 -- 1824.

Digital Library

[9]

Al-Omari, S., Sumari, P., Al-Taweel, S. 2009. Digital recognition using neural network. Journal of Computer Science. 5, 6 (June 2009), 427--434.

[10]

Patil, V., and Shimpi, S. 2011. Handwritten english character recognition using neural network. Computer Science and Engineering. 41 (Nov. 2011), 5587--5591.

[11]

Lecun, Y., Bottou, L., Bengio, Y., and Haffner, P. 1998. Gradient-based learning applied to document recognition. In Proceedings of the IEEE. 86, 11 (Nov. 1998), 2278--2324.

[12]

Niu, X. X., Suen, C. Y. 2012. A novel hybrid CNN-SVM classifier for recognizing handwritten digits. Pattern Recognition. 45, 4 (2012), 1318--1325.

Digital Library

[13]

Maitra, D. S., Bhattacharya, U., Parui, S. K. 2015. CNN based common approach to handwritten character recognition of multiple scripts. In International Conference on Document Analysis and Recognition (ICDAR), Tunis, Tunisia (Aug. 2015), 1021--1025.

Digital Library

[14]

Guo, Q., Wang, F. L., Lei, J., Tu, D., Li, G. H. 2016. Convolutional feature learning and Hybrid CNN-HMM for scene number recognition. Neurocomputing. 184, 5 (April 2016), 78--90.

Digital Library

[15]

Qiao, J. F., Wang, G. M., Li, W. J., Chen, M. 2018. An adaptive deep Q-learning strategy for handwritten digit recognition. Neural Networks. 107 (Nov. 2018), 61--71.

[16]

Hori, T., Watanabe, S., Zhang, Y., Chan, W. 2017. Advances in joint CTC-attention based end-to-end speech recognition with a deep CNN encoder and RNN-LM. American Physical Society, arxiv.org/abs/1706.02737 (June 2017).

[17]

Cho, K., Merrienboer, B. V., Gulcehre, C. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. Computer Science. (Sep 2014).

[18]

Hochreiter, S., Schmidhuber, J. 1997. Long short-term memory. Neural Computation. 9, 8 (Nov. 1997), 1735--1780.

Digital Library

[19]

Srivastava, N., Hinton, G., Krizhevsky, A., et al. 2014. Dropout: A simple way to prevent neural networks from over fitting. The Journal of Machine Learning Research. 15, 1 (2014), 1929--1958.

Digital Library

[20]

Gal, Y., Ghahramani, Z. 2016. A theoretically grounded application of dropout in recurrent neural networks. In Advances in Neural Information Processing Systems 29 (NIPS), Barcelona, Spain (2016).

Digital Library

[21]

http://yann.lecun.com/exdb/mnist/, The MNIST database of handwritten digits.

Cited By

Zeng QGuo SCao RZhao ZDuan H(2024)Legal Transition Sequence Recognition of a Bounded Petri Net Using a Gate Recurrent UnitIEEE Transactions on Big Data10.1109/TBDATA.2023.331925210:1(66-76)Online publication date: Feb-2024
https://doi.org/10.1109/TBDATA.2023.3319252
Moulishwar VKarthikeyan PKumar VSrihariharan A(2024)EXTENSION FOR HANDWRITTEN CHARACTER RECOGNITION USING RNN-GRU ALGORITHM2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)10.1109/IConSCEPT61884.2024.10627915(1-6)Online publication date: 4-Jul-2024
https://doi.org/10.1109/IConSCEPT61884.2024.10627915
Sher MMinallah NFrnda JKhan W(2024)Elevating Crop Classification Performance Through CNN-GRU Feature FusionIEEE Access10.1109/ACCESS.2024.346719312(141013-141025)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3467193
Show More Cited By

Index Terms

Hybrid CNN-GRU model for high efficient handwritten digit recognition
1. Computing methodologies
  1. Computer graphics
    1. Image manipulation
      1. Image processing
  2. Machine learning
    1. Machine learning approaches
      1. Neural networks

Recommendations

Handwritten Digits Recognition Based on Deep Learning4j
AIPR '18: Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition

Over the past few decades, Optical Character Recognition (OCR), particularly handwriting recognition, has received much attention. Handwritten Digits Recognition (HDR) means, receive and comprehend handwriting inputs from different sources for example ...
Hybrid CNN-SVM Classifier for Handwritten Digit Recognition
Abstract
The aim of this paper is to develop a hybrid model of a powerful Convolutional Neural Networks (CNN) and Support Vector Machine (SVM) for recognition of handwritten digit from MNIST dataset. The proposed hybrid model combines the key properties of ...
Improved handwritten digit recognition using artificial neural networks

Handwritten digit recognition is one of the significant challenging problems, finding usage in fields like postal mail arranging and healthcare. Thus, it evokes the necessity for a framework that can apprehend the penmanship of all age groups with ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Other conferences

AIPR '19: Proceedings of the 2nd International Conference on Artificial Intelligence and Pattern Recognition

August 2019

198 pages

ISBN:9781450372299

DOI:10.1145/3357254

Conference Chairs:
Li Ma
North China University of Technology, China
,
Xu Huang
University of Canberra, Australia

Copyright © 2019 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 16 August 2019

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

the National Natural Science Foundation of China
the Natural Science Foundation of Shaanxi Province, China
the innovation wisdom base for wide bandgap semiconductor and micro-nano electronics of China
Strategic international scientific and technological innovation cooperation key projects

Conference

AIPR 2019

AIPR 2019: 2019 2nd International Conference on Artificial Intelligence and Pattern Recognition

August 16 - 18, 2019

Beijing, China

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

15
Total Citations
View Citations
448
Total Downloads

Downloads (Last 12 months)28
Downloads (Last 6 weeks)3

Reflects downloads up to 01 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

Zeng QGuo SCao RZhao ZDuan H(2024)Legal Transition Sequence Recognition of a Bounded Petri Net Using a Gate Recurrent UnitIEEE Transactions on Big Data10.1109/TBDATA.2023.331925210:1(66-76)Online publication date: Feb-2024
https://doi.org/10.1109/TBDATA.2023.3319252
Moulishwar VKarthikeyan PKumar VSrihariharan A(2024)EXTENSION FOR HANDWRITTEN CHARACTER RECOGNITION USING RNN-GRU ALGORITHM2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)10.1109/IConSCEPT61884.2024.10627915(1-6)Online publication date: 4-Jul-2024
https://doi.org/10.1109/IConSCEPT61884.2024.10627915
Sher MMinallah NFrnda JKhan W(2024)Elevating Crop Classification Performance Through CNN-GRU Feature FusionIEEE Access10.1109/ACCESS.2024.346719312(141013-141025)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3467193
Abdulraheem ASuleiman JJung I(2023)Enhancing the Automatic Recognition Accuracy of Imprinted Ship Characters by Using Machine LearningSustainability10.3390/su15191413015:19(14130)Online publication date: 24-Sep-2023
https://doi.org/10.3390/su151914130
Abdulraheem AJung I(2023)Effective Digital Technology Enabling Automatic Recognition of Special-Type Marking of Expiry DatesSustainability10.3390/su15171291515:17(12915)Online publication date: 26-Aug-2023
https://doi.org/10.3390/su151712915
Shao HMa EZhu MDeng XZhai S(2023)MNIST Handwritten Digit Classification Based on Convolutional Neural Network with Hyperparameter OptimizationIntelligent Automation & Soft Computing10.32604/iasc.2023.03632336:3(3595-3606)Online publication date: 2023
https://doi.org/10.32604/iasc.2023.036323
Márton ZSzalay IFodor D(2023)Convolutional Neural Network-Based Tire Pressure Monitoring SystemIEEE Access10.1109/ACCESS.2023.329440811(70317-70332)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3294408
Sakshi Kukreja V(2023)Recent trends in mathematical expressions recognition: An LDA-based analysisExpert Systems with Applications10.1016/j.eswa.2022.119028213(119028)Online publication date: Mar-2023
https://doi.org/10.1016/j.eswa.2022.119028
Mathew TS. R S(2022)COVID-19 and Pneumonia Detection using Hybrid VGG-16 model using Chest X-rays2022 International Conference on Innovations in Science and Technology for Sustainable Development (ICISTSD)10.1109/ICISTSD55159.2022.10010392(287-292)Online publication date: 25-Aug-2022
https://doi.org/10.1109/ICISTSD55159.2022.10010392
Hasib Uddin AKhatun JAfroz Meghna MMahmud P(2022)Bangla Handwritten Digit Recognition using RNN-CNN Hybrid Approach2022 25th International Conference on Computer and Information Technology (ICCIT)10.1109/ICCIT57492.2022.10055089(288-293)Online publication date: 17-Dec-2022
https://doi.org/10.1109/ICCIT57492.2022.10055089
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents