Pattern Recognition and Image Analysis

, Volume 22, Issue 2, pp 360–370

Scale-space line curvature estimation for straight line and circle detection

  • E. V. Semeikina
  • D. V. Yurin
  • A. S. Krylov
  • Kuo-Liang Chung
  • Yong-Huai Huang
Representation, Processing, Analysis, and Understanding of Images

DOI: 10.1134/S1054661812020137

Cite this article as:
Semeikina, E.V., Yurin, D.V., Krylov, A.S. et al. Pattern Recognit. Image Anal. (2012) 22: 360. doi:10.1134/S1054661812020137

Abstract

A scale-space algorithm for estimating the local curvature of lines (edges or isolines) is presented. Two variants of edge curvature estimation based on differential invariants are suggested and compared. The first variant uses the edge curvature formula derived in the paper and the second is based on image preprocessing, which allows one to use the isoline curvature formula for edge curvature estimation. An analysis of scale selection needed to reach a desired accuracy is presented. Also, noise influence analysis has been performed. The application of curvature estimation to detection of straight lines and circles is suggested and implemented. Curvature information usage in parametric curve detection speeds up search algorithms and makes the results more stable.

Keywords

edge curvature isoline curvature scale-space straight line detection circle detection 

Copyright information

© Pleiades Publishing, Ltd. 2012

Authors and Affiliations

  • E. V. Semeikina
    • 1
  • D. V. Yurin
    • 1
  • A. S. Krylov
    • 1
  • Kuo-Liang Chung
    • 2
  • Yong-Huai Huang
    • 3
  1. 1.Laboratory of Mathematical Methods of Image Processing, Faculty of Computational Mathematics and CyberneticMoscow State UniversityMoscowRussia
  2. 2.Department of Computer Science and Information EngineeringNational Taiwan University of Science and TechnologyTaipei, TaiwanR.O.C.
  3. 3.Institute of Computer and Communication Engineering and Department of Electronic Engineering Jinwen University of Science and TechnologyHsin-Tien, TaipeiTaiwan, R.O.C.

Personalised recommendations