Implementation of a fast post-processing algorithm of geometrical coding of digital images using CUDA architecture

The paper presents some improvements of fast contour recognition algorithm. The main idea of this algorithm is based on calculation of geometric characteristics of a two-dimensional surface in $R^3$, which encodes digital images. To obtain the contours, Minkowski fractal dimension calculation is used. A post-processing algorithm of contour thinning without loss of quality of entire contour picture is proposed in the paper. An estimate of the speed of the new algorithm is presented in comparison with the well-known implementation of the Canny algorithm using the OpenCV computer vision library and the parallel architecture of CUDA. Examples demonstrating the efficiency of the new algorithm are presented.