local-guru.net http://www.local-guru.net/blog 40 http://www.local-guru.net//blog/2010/1/19/line-detection-with-hough-transform <p>I wrote a small processing sketch to work out how linedetection using <a href="http://en.wikipedia.org/wiki/Hough_transform">hough-transform</a> works.</p> <p><a href="http://www.local-guru.net/processing/hough_transform">click here</a> to see it in action and get the sourcecode. the code is not optimised for speed but for my understanding :-) so don't complain if it doesn't work on live-video.</p> <p>the algorithm takes a image that has run through an edge detection algorithm and turned into a black/white image and find where things like edges or circles are by converting the pixels from imagespace to a parameterspace where such detection is much easyer.</p> <p>for each pixel that is set in the source image a set of parameters that satisfy the formular r = x * cos(roh) + y * sin(roh) is calculated and r and roh are plotted as the parameterspace image</p> <p>every line in the input image results in a bunch of lines in the parameterspace that have a common intersection point.</p> <p>in my example i use a input image like this</p> <p><img src="http://www.local-guru.net/img/guru/hough_input.png" alt="input" /></p> <p>calculate how it looks in parameter space</p> <p><img src="http://www.local-guru.net/img/guru/hough_parameter.png" alt="parameter space" /></p> <p>and then reconstruct where the lines are</p> <p><img src="http://www.local-guru.net/img/guru/hough_reconstruct.png" alt="reconstruct" /></p> 2010-01-19T03:23:00+01:00