Visually Similar Handwritten Chinese Character Recognition with Convolutional Neural Network

Wei Han Liu, Kian Ming Lim, Chin Poo Lee

Research output: Chapter in Book/Conference proceedingConference contributionpeer-review

4 Citations (Scopus)

Abstract

Computer vision has penetrated many domains, for instance, security, sports, health and medicine, agriculture, transportation, manufacturing, retail, and so like. One of the computer vision tasks is character recognition. In this work, a visually similar handwritten Chinese character dataset is collected. Subsequently, an enhanced convolutional neural network is proposed for the recognition of visually similar handwritten Chinese characters. The convolutional neural network is enhanced by the dropout regularization and early stopping mechanism to reduce the overfitting problem. The Adam optimizer is also leveraged to accelerate and optimize the training process of the convolutional neural network. The empirical results demonstrate that the enhanced convolutional neural network achieves a 97% accuracy, thus corroborate it has better discriminating power in visually similar handwritten Chinese character recognition.

Original languageEnglish
Title of host publication2021 9th International Conference on Information and Communication Technology, ICoICT 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages175-179
Number of pages5
ISBN (Electronic)9781665404471
DOIs
Publication statusPublished - 3 Aug 2021
Externally publishedYes
Event9th International Conference on Information and Communication Technology, ICoICT 2021 - Virtual, Yogyakarta, Indonesia
Duration: 3 Aug 20215 Aug 2021

Publication series

Name2021 9th International Conference on Information and Communication Technology, ICoICT 2021

Conference

Conference9th International Conference on Information and Communication Technology, ICoICT 2021
Country/TerritoryIndonesia
CityVirtual, Yogyakarta
Period3/08/215/08/21

Keywords

  • Chinese character recognition
  • CNN
  • convolutional neural network
  • handwritten Chinese character recognition
  • visually similar handwritten Chinese character recognition

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Hardware and Architecture
  • Information Systems

Fingerprint

Dive into the research topics of 'Visually Similar Handwritten Chinese Character Recognition with Convolutional Neural Network'. Together they form a unique fingerprint.

Cite this