Hough's transform for circle detection

The thesis is focused on the implementation of Hough transform algorithm for circle recognition. Algorithm is implemented in C++ language using open source library OpenCv. As a development environment was chosen Microsoft Visual Studio 2008. At first there is general description of classical Hough transform for line and circle recognition. Then thesis contains description of particular steps of Hough transform algorithm and description of OpenCv functions witch are used in these steps. There is a detail description of functions for converting image to grayscale, smoothing image by Gaussian filter and Canny edge detector for edge detecting in smoothed image. Efficiency and speed of algorithm is increased by using function for finding possible centers. This function using the fact that line perpendicular to the chord of circle and going thought its middle point at the same time have to cross the center of the circle. Results of particular stages of algorithm (converting to grayscale, smoothing by Gaussian filter, edge detection, creating of possible centers accumulator and drawing circles) are presented on ultrasonic image of collagen arterial substitute. In the second part of the thesis the algorithm is used for detection of artery in frames of video captured by ultrasound. There is a description of automatic method for evaluating of success of artery detection. Success of detection is analyzed by changing values of important algorithm parameters. From series of tests there are defined ideal parameters of algorithm for artery detection in the video