Skip to main navigation Skip to search Skip to main content

Skew detection and correction based on Hough transform and Harris corners

  • LIPI

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

Abstract

Skew angle detection is one of the most important component of Optical Characters Recognition (OCR) systems and documents analysis. Taking documents by the blind and visually impaired people with a mobile phone always have a degree of inclination. In this paper, a novel and an efficient method based on extraction of Harris corner features points and Hough transform is presented to estimate skew angle of printed documents. A comparative study using the ICDAR2015 database with the well-known methods in literature, shown the effectiveness and the performance of the proposed algorithm.

Original languageEnglish
Title of host publication2017 International Conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2017
EditorsSaad Bennani Dosse, Younes Lakhrissi, Anass Mansouri, Hakim El Fadili
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509066810
DOIs
Publication statusPublished - 26 May 2017
Event2017 International Conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2017 - Fez, Morocco
Duration: 19 Apr 201720 Apr 2017

Publication series

Name2017 International Conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2017

Conference

Conference2017 International Conference on Wireless Technologies, Embedded and Intelligent Systems, WITS 2017
Country/TerritoryMorocco
CityFez
Period19/04/1720/04/17

Keywords

  • Blind and visually impaired people
  • Detection and correction of inclination
  • Harris Corner features
  • Hough Transform

Fingerprint

Dive into the research topics of 'Skew detection and correction based on Hough transform and Harris corners'. Together they form a unique fingerprint.

Cite this