Chord midpoint Hough transform based ellipse detection method

A new method called chord midpoint Hough transform (CMHT) was proposed to improve the efficiency and accuracy of ellipse detection in an image. This method is based on the fact that a chord passing through the center of an ellipse is divided into bisection. As a result, the term "inscribed ellipse" was introduced, and all inscribed ellipses of an ellipse must pass its center. The algorithm mainly consists of extracting black and white edge images, scanning the edge images according to the distribution of pixels, accumulating of 2D accumulator, and finally computing the ellipse's positions and other parameters. In comparison with other detection algorithms, such as standard Hough transform (SHT) and random 3 dots Hough transform (RHT-3), this algorithm has higher speed and detection accuracy.