Text detection in bus panel for visually impaired people "seeing" bus route number

Chun Ming Tsai*, Zong Mu Yeh

*Corresponding author for this work

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

6 Citations (Scopus)

Abstract

A text detection method is proposed to help visually impaired persons to "see" bus route numbers in the text region on the bus panel. Because the bus will be moving, the proposed method includes moving bus detection, bus panel detection, and text detection to detect the moving bus, bus panel, and text region, respectively. Experimental results show that the performance of the proposed method is better than conventional two frame differencing method. Furthermore, the proposed method reduces the time complexity and has 100% text detection rate for the training and testing video.

Original languageEnglish
Title of host publicationProceedings - International Conference on Machine Learning and Cybernetics
PublisherIEEE Computer Society
Pages1234-1239
Number of pages6
ISBN (Electronic)9781479902576
DOIs
Publication statusPublished - 2013
Event12th International Conference on Machine Learning and Cybernetics, ICMLC 2013 - Tianjin, China
Duration: 2013 Jul 142013 Jul 17

Publication series

NameProceedings - International Conference on Machine Learning and Cybernetics
Volume3
ISSN (Print)2160-133X
ISSN (Electronic)2160-1348

Other

Other12th International Conference on Machine Learning and Cybernetics, ICMLC 2013
Country/TerritoryChina
CityTianjin
Period2013/07/142013/07/17

Keywords

  • Bus panel detection
  • Moving bus detection
  • Text detection
  • Visually impaired person

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computational Theory and Mathematics
  • Computer Networks and Communications
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Text detection in bus panel for visually impaired people "seeing" bus route number'. Together they form a unique fingerprint.

Cite this