Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Int J Adv Manuf Technol (1999) 15:96102 1999 Springer-Verlag London Limited

Summary: Int J Adv Manuf Technol (1999) 15:96102
1999 Springer-Verlag London Limited
Coarse-to-Fine Search Technique to Detect Circles in Images
M. Atiquzzaman
Department of Electrical and Computer Engineering, University of Dayton, Dayton, OH, USA
Detection of patterns in images is an important high-level task
in automated manufacturing using machine vision. Straight
lines, circles and ellipses are considered to be the basic
building blocks of a large number of patterns occurring in
real-world images. Real-world images frequently contain noise
and occlusions resulting in discontinuous patterns in noisy
images. The Hough transform can be used to detect parametric
patterns, such as straight lines and circles, embedded in noisy
images. The large amount of storage and computing power
required by the Hough transform presents a problem in real-
time applications.
The aim of this paper is to propose an efficient coarse-to-
fine search technique to reduce the storage and computing
time in detecting circles in an image. Variable-sized images
and accumulator arrays are used to reduce the computing and


Source: Atiquzzaman, Mohammed - School of Computer Science, University of Oklahoma
Pizurica, Aleksandra - Department of Telecommunications and Information Processing, Universiteit Gent


Collections: Computer Technologies and Information Sciences; Engineering