Amarbold Purev, Hiroaki Wagatsuma
Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology, 2-4 Hibikino, Wakamatsu, Kitakyushu 808-0196, Japan
pp. 185–192
ABSTRACT
The most common algorithm for detecting straight lines in a digital image is the Hough Transform method. The method involves two consecutive steps: transforming the image edge location onto parameter space and voting procedure to acquire line characteristics. The former deals in continuous space, and the latter counts votes in a discrete matrix, making the algorithm sensitive to noise. We transformed each image pixel location to the parameter space as a Hough line and generated a nonlinear oscillator to attract them into the intersection with other lines. This concept could contribute to a line detection problem in image processing using a consistent mathematical description.

ARTICLE INFOArticle History
Received 25 November 2022
Accepted 26 April 2023

Keywords
Hough transform
Line detection
Nonlinear dynamics
Coupled nonlinear oscillators
Kuramoto model

JAALR3401

Download article(PDF)