Skip to main navigation Skip to search Skip to main content

Multi-experts for touching digit string recognition

  • SUNY Buffalo

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

17 Scopus citations

Abstract

84.6% of touching digit strings have only two digits touching, 12.3% have three digits touching and 3.1% have more than three digits touching. We present a multi-expert approach to recognize touching digit pairs (TDP) and touching digit triples (TDT). We combine holistic and traditional segmentation methods. 25,686 TDP training samples and 2,778 TDP testing samples collected from USPS mail are used in our experiment. The holistic method outperforms the traditional segmentation-based methods. The multi-expert combination has the best performance: a correct recognition rate of 91.1% on TDP.

Original languageEnglish
Title of host publicationProceedings of the 5th International Conference on Document Analysis and Recognition, ICDAR 1999
PublisherIEEE Computer Society
Pages804-807
Number of pages4
ISBN (Electronic)0769503187
DOIs
StatePublished - 1999
Event5th International Conference on Document Analysis and Recognition, ICDAR 1999 - Bangalore, India
Duration: Sep 20 1999Sep 22 1999

Publication series

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

Conference

Conference5th International Conference on Document Analysis and Recognition, ICDAR 1999
Country/TerritoryIndia
CityBangalore
Period09/20/9909/22/99

Fingerprint

Dive into the research topics of 'Multi-experts for touching digit string recognition'. Together they form a unique fingerprint.

Cite this