Skip to main navigation Skip to search Skip to main content

Text feature extraction of natural scenes using Gabor wavelet transformation based on scale overlapping

  • Fang Yin*
  • , Deyun Chen
  • , Rui Wu
  • *Corresponding author for this work
  • Harbin University of Science and Technology
  • School of Computer Science and Technology, Harbin Institute of Technology

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

Abstract

The features of scene text images determine the scene text low-quality. Existing method can not handle the issue. A method is proposed in the paper which makes use the frequency and direction selectivity of Gabor function and constructs a suitable wavelet transform to extract the feature of characters. And further the improved Gabor wavelet based on scale overlapping is proposed. The scale overlap reinforces the selection of Gabor filters to strokes width. Thus, a high robustness feature is obtained. The experiments show that the method is with good performance and is able to deal effectively with low-quality texts.

Original languageEnglish
Title of host publicationProceedings of the 6th International Forum on Strategic Technology, IFOST 2011
Pages1062-1064
Number of pages3
DOIs
StatePublished - 2011
Externally publishedYes
Event6th International Forum on Strategic Technology, IFOST 2011 - Harbin, China
Duration: 22 Aug 201124 Aug 2011

Publication series

NameProceedings of the 6th International Forum on Strategic Technology, IFOST 2011
Volume2

Conference

Conference6th International Forum on Strategic Technology, IFOST 2011
Country/TerritoryChina
CityHarbin
Period22/08/1124/08/11

Keywords

  • Feature extraction
  • Gabor wavelet transform
  • Low-quality text
  • Scale overlapping

Fingerprint

Dive into the research topics of 'Text feature extraction of natural scenes using Gabor wavelet transformation based on scale overlapping'. Together they form a unique fingerprint.

Cite this