Improving handwritten Chinese text recognition by confidence transformation

Qiu Feng Wang*, Fei Yin, Cheng Lin Liu

*Corresponding author for this work

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

18 Citations (Scopus)

Abstract

This paper investigates the effects of confidence transformation (CT) of the character classifier outputs in handwritten Chinese text recognition. The classifier outputs are transformed to confidence values in three confidence types, namely, sigmoid, soft max and Dempster-Shafer theory of evidence (D-S evidence). The confidence parameters are optimized by minimizing the cross-entropy (CE) loss function (both binary and multi-class) on a validation dataset, where we add non-character samples to enhance the outlier rejection capability in text recognition. Experimental results on the CASIA-HWDB database show that confidence transformation improves the handwritten text recognition performance significantly and adding non-characters for confidence parameter estimation is beneficial. Among the confidence types, the D-S evidence performs best.

Original languageEnglish
Title of host publicationProceedings - 11th International Conference on Document Analysis and Recognition, ICDAR 2011
Pages518-522
Number of pages5
DOIs
Publication statusPublished - 2011
Externally publishedYes
Event11th International Conference on Document Analysis and Recognition, ICDAR 2011 - Beijing, China
Duration: 18 Sept 201121 Sept 2011

Publication series

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

Conference

Conference11th International Conference on Document Analysis and Recognition, ICDAR 2011
Country/TerritoryChina
CityBeijing
Period18/09/1121/09/11

Keywords

  • Handwritten text recognition
  • confidence transformation
  • cross-entropy
  • non-characters

Fingerprint

Dive into the research topics of 'Improving handwritten Chinese text recognition by confidence transformation'. Together they form a unique fingerprint.

Cite this