Text detection in natural and computer-generated images

Azmi Can Özgen, Mandana Fasounaki, Hazim Kemal Ekenel

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

Abstract

Text detection is one of the most challenging and commonly dealt applications in computer vision. Detecting text regions is the first step of the text recognition systems called Optical Character Recognition. This process requires the separation of text region from non-text region. In this paper, we utilize Maximally Stable Extremal Regions to acquire very first text region candidates. Then these possible regions are reduced in quantity by using geometric and stroke width properties. Candidate regions are joined to obtain text groups. Finally, Tesseract Optical Character Recognition engine is utilized as the last step to eliminate non-text groups. We evaluated the proposed system on KAIST and ICDAR datasets for both natural images and computer-generated images. For natural images 82.7% precision and 52.0% f-accuracy; for computer-generated images 64.0% precision and 65.2% f-accuracy is achieved.

Original languageEnglish (US)
Title of host publication26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1-4
Number of pages4
ISBN (Electronic)9781538615010
DOIs
StatePublished - Jul 5 2018
Event26th IEEE Signal Processing and Communications Applications Conference, SIU 2018 - Izmir, Turkey
Duration: May 2 2018May 5 2018

Publication series

Name26th IEEE Signal Processing and Communications Applications Conference, SIU 2018

Conference

Conference26th IEEE Signal Processing and Communications Applications Conference, SIU 2018
Country/TerritoryTurkey
CityIzmir
Period5/2/185/5/18

Keywords

  • Geometric and stroke width properties
  • Maximally stable extremal regions
  • Non-text region elimination
  • Text detection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing

Fingerprint

Dive into the research topics of 'Text detection in natural and computer-generated images'. Together they form a unique fingerprint.

Cite this