Contour estimation in images using virtual signals

摘要: The line-fitting problem has been transposed to the signal-processing framework: Array-processing methods can be applied virtual signals generated from image, estimate straight-line orientations. This paper deals with estimation of straight and distorted lines in images by fast array-processing methods. Hough transform snake retrieve contours, but present limitations. We adapt a high-resolution method, propagator multiple contours. For first time, method is proposed cope intrinsically limited size images, which reduces accuracy due low number signal realizations. Moreover, an extension impaired correlated noise proposed. this, subspace-based based on higher-order statistics Distorted contours are assimilated wavefronts retrieved novel optimization method. performance validated several images.