Skip to main navigation Skip to search Skip to main content

Text search: Towards fast text localization in scene images

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

1 Scopus citations

Abstract

We present an efficient approach to text localization. We restrict our attention to the text localization and refer to our method as 'text search'. In particular, we pre-trained a text detection ConvNet which skip the region proposal process, and integrates bounding boxes and text confidence score into the output layer. Our approach achieved similar high precision with [1], and acceptable level of recall.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE International Symposium on Multimedia, ISM 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages83-86
Number of pages4
ISBN (Electronic)9781509045709
DOIs
StatePublished - 18 Jan 2017
Externally publishedYes
Event18th IEEE International Symposium on Multimedia, ISM 2016 - San Jose, United States
Duration: 11 Dec 201613 Dec 2016

Publication series

NameProceedings - 2016 IEEE International Symposium on Multimedia, ISM 2016

Conference

Conference18th IEEE International Symposium on Multimedia, ISM 2016
Country/TerritoryUnited States
CitySan Jose
Period11/12/1613/12/16

Keywords

  • ConvNet
  • Region proposals
  • Text localization

Fingerprint

Dive into the research topics of 'Text search: Towards fast text localization in scene images'. Together they form a unique fingerprint.

Cite this