Fast shape detection using Hough transform by raster operation

Abstract

To detect arbitrary shapes on a binary image quickly, a method is developed for performing the principle of the Hough transform by means of the raster operation (bitblt) hardware, with which a workstation is equipped. The Boolean operations among bitmaps of images are used to search candidate patterns corresponding to a given shape. Using the bitblt hardware, those operations can be carried out rapidly. The method is applicable not only for shape recognition but also line detection.<>