Handwritten Bangla digit recognition using hierarchical Bayesian network

  • Jin Wen Xu*
  • , Jinhua Xu
  • , Yue Lu
  • *Corresponding author for this work

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

15 Scopus citations

Abstract

A hierarchical Bayesian network is used for handwritten Bangla digit recognition. Rather than extracted feature vectors, original digit images are used as the network input directly. The network is trained on handwritten samples. And then it's tested on untrained images and hand-drawn digits. An average recognition accuracy of 87.5 is achieved. The system exhibits robust invariant recognition with respect to considerable object noise which is quite common in handwritten digits.

Original languageEnglish
Title of host publicationProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008
Pages1096-1099
Number of pages4
DOIs
StatePublished - 2008
EventProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008 - Xiamen, China
Duration: 17 Nov 200819 Nov 2008

Publication series

NameProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008

Conference

ConferenceProceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008
Country/TerritoryChina
CityXiamen
Period17/11/0819/11/08

Fingerprint

Dive into the research topics of 'Handwritten Bangla digit recognition using hierarchical Bayesian network'. Together they form a unique fingerprint.

Cite this