Scene Text Recognition Based on Positional Relation between Closed Curves

Yuji Waizumi, Kazuyuki Tanaka

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Scene text recognition has attracted much attention in the research community. Many proposed scene text recognition methods adopt a step-by-step procedure, which includes a text extraction phase and a recognition phase. In this study, in order to eliminate the risk of text extraction error, we try to build a scene text recognition system that does not involve the text extraction phase. In our proposed method, an image is viewed as a set of closed curves, and text is extracted and recognized simultaneously from the image by combining the closed curves. Through experiments, we demonstrate the recognition accuracy of our proposed method.

Original languageEnglish
Title of host publicationProceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014
EditorsDavid Al-Dabass, Gregorio Romero, Emilio Corchado, Athanasios Pantelous, Ismail Saad, Alessandra Orsoni
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages182-186
Number of pages5
ISBN (Electronic)9781479975990
DOIs
Publication statusPublished - 2014 May 5
Event2nd IEEE International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014 - Madrid, Spain
Duration: 2014 Nov 182014 Nov 20

Publication series

NameProceedings - 2nd International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014

Other

Other2nd IEEE International Conference on Artificial Intelligence, Modelling, and Simulation, AIMS 2014
CountrySpain
CityMadrid
Period14/11/1814/11/20

Keywords

  • Gaussian distribution
  • closed curves
  • scene text recognition

ASJC Scopus subject areas

  • Modelling and Simulation
  • Computer Science(all)

Fingerprint Dive into the research topics of 'Scene Text Recognition Based on Positional Relation between Closed Curves'. Together they form a unique fingerprint.

Cite this