Pocket Change: Circle Recognition 1.2 2006/12/19 00:08:21 US/Central 2006/12/19 01:57:10.014 US/Central Tyler James Barth tbar@rice.edu Aaron David Cottle acottle@rice.edu John P Stallcup john.stallcup@rice.edu Christopher J. Vaucher cvaucher@rice.edu Tyler James Barth tbar@rice.edu Aaron David Cottle acottle@rice.edu John P Stallcup john.stallcup@rice.edu Christopher J. Vaucher cvaucher@rice.edu coin recognition image recognition machine vision pocket change signal processing A description of the process by which to determine the center and radius of each circle. Given an image, the first step is locating the coins in the scene. Only then can you make a comparison. Many different methods are available for finding circles in images. Initially, you might want to try edge detection on the image and then code an algorithm that would, based on the located edges, determine the center of the circle. However, you will find that circle recognition is a commonly performed task with established algorithms. For our project, we found a user friendly circle location Matlab function that implements the Circular Hough Transform in the MATLAB code repository. For more information about the Hough Transform you can go here. Once you have the radii and centers of the circles, you can then move to coin identification.