Combination of ResNet and Center Loss Based Metric Learning for Handwritten Chinese Character Recognition

  • Ruyu Zhang
  • , Qingqing Wang
  • , Yue Lu

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

27 Scopus citations

Abstract

Nowdays, deep networks have played a dominant role in the filed of handwritten Chinese character recognition(HCCR), and their recognition performance have reported to surpass human beings significantly. Recent research shows that the performance of deep networks has been further improved with the assistance of metric learning, since more inter-class and intra-class information can be captured. Center loss is a powerful metric learning strategy, and has no necessity of selecting sample units compared with other metric learning strategies. In this paper, we explore the effectiveness of the center loss based metric learning in boosting deep networks for the task of HCCR. By combining with the residual network (ResNet), an accuracy of 97.03% has been achieved on the ICDAR-2013 dataset, which is much higher than the deep networks without metric learning.

Original languageEnglish
Title of host publicationProceedings - 1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017
PublisherIEEE Computer Society
Pages25-29
Number of pages5
ISBN (Electronic)9781538635865
DOIs
StatePublished - 2 Jul 2017
Event1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017 - Kyoto, Japan
Duration: 11 Nov 2017 → …

Publication series

NameProceedings of the International Conference on Document Analysis and Recognition, ICDAR
Volume5
ISSN (Print)1520-5363

Conference

Conference1st Workshop of Machine Learning under International Conference on Document Analysis and Recognition, ICDAR-WML 2017
Country/TerritoryJapan
CityKyoto
Period11/11/17 → …

Keywords

  • Center loss
  • HCCR
  • Metric learning
  • ResNet

Fingerprint

Dive into the research topics of 'Combination of ResNet and Center Loss Based Metric Learning for Handwritten Chinese Character Recognition'. Together they form a unique fingerprint.

Cite this