HOUGH TRANSFORM BASED IMAGE REGISTRATION

Image registration is the process of overlaying images (two or more) of the same scene taken at different times, from different viewpoints, and/or by different sensors. The Hough transform is a method for detecting curves by exploiting the duality between points on a curve and parameters of that curve. Hough transform theory images by generating the peak point from gray scale images, and seek for the effect caused by the distance and the angles. Lines will appear on the edge of images, which has been processed edge detection theorem. The input to a Hough transform is normally an image that has been edge detected with a Robert, Sobel or Canny edge detector, for instance. To simplify the computation, the parameter can be divided into distance and angles parameters where both parameter to achieve the enhancement of straight line detection using Hough Transform. In this case it is more like a pattern matcher. Even though that the Hough transform is invariant to rotation. Finally, the input images are registered using the estimated rotation parameter.