Combined spatial and transform domain analysis for rectangle detection

Harish Bhaskar, Naoufel Werghi, Saeed Al Mansoori

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

12 Scopus citations

Abstract

We describe and compare methods for detecting rectangles in images using Hough and Radon transforms. Locating rectangles in a new image involves an alternating scheme of transform peak extraction and peak filtering. During the step of peak extraction, we apply the hough/radon transform on the target image and extract peaks (corresponding to line segments) from the transformed image. We filter these peaks based on certain geometric constraints in the transform and spatial constraints on the coordinate (or image) domain such that every set of 4 filtered peaks correspond to a rectangle in the image. We explore the effect of model parameters on system performance and show that the proposed methods achieves good accuracy for rectangle detection on several synthetic and real datasets.

Original languageBritish English
Title of host publication13th Conference on Information Fusion, Fusion 2010
StatePublished - 2010
Event13th Conference on Information Fusion, Fusion 2010 - Edinburgh, United Kingdom
Duration: 26 Jul 201029 Jul 2010

Publication series

Name13th Conference on Information Fusion, Fusion 2010

Conference

Conference13th Conference on Information Fusion, Fusion 2010
Country/TerritoryUnited Kingdom
CityEdinburgh
Period26/07/1029/07/10

Keywords

  • Aerial images
  • Hough
  • Licence plate
  • Radon
  • Rectangle detection
  • Spatial constraints
  • Transform domain

Fingerprint

Dive into the research topics of 'Combined spatial and transform domain analysis for rectangle detection'. Together they form a unique fingerprint.

Cite this