Text detection from natural scene images using scale space model

Qiaoyu Sun, Yue Lu

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

3 Scopus citations

Abstract

A scale space based approach is proposed to detect text from natural scene images with complicated background. An edge map containing the edge information of four directions is obtained by Sobel operators. Character areas are detected by connected components analysis and are merged into candidate text regions. We construct a N-level scale space model and compute spatial responses to the Laplacian-of- Gaussian operator at these scale levels. The distribution of some strongest responses obtained from scale space model is employed to verify whether a candidate is a true text region or not. The experimental results demonstrate that the proposed method is able to effectively filter the nontext regions and locate text regions in natural scene images with complicated background.

Original languageEnglish
Title of host publicationAdvances on Digital Television and Wireless Multimedia Communications - 9th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2012, Proceedings
Pages156-161
Number of pages6
DOIs
StatePublished - 2012
Event9th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2012 - Shanghai, China
Duration: 9 Nov 201210 Nov 2012

Publication series

NameCommunications in Computer and Information Science
Volume331 CCI
ISSN (Print)1865-0929

Conference

Conference9th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2012
Country/TerritoryChina
CityShanghai
Period9/11/1210/11/12

Keywords

  • Connected Components Analysis
  • Edge Detection
  • Laplacian-of-Gaussian operator
  • Scale Space
  • Text Detection

Fingerprint

Dive into the research topics of 'Text detection from natural scene images using scale space model'. Together they form a unique fingerprint.

Cite this