Method of Hardware Selection of Characteristic Features Based on Radon Transformation and not Sensitive to Rotation, Shifting and Scale of the Input Images

Abstract

In this paper considered by the method of the organization of cellular automata to extract characteristic features of images based on the Radon transform. Cellular automata are constructed using a hexagonal surface. This increases the efficiency of image recognition. This made it possible to implement the Radon transform on the six directions. This cellular automata was simulated in the software environment of Active-HDL, and also was created his software model. Experimental studies for both models showed high results of recognition for the different levels of noise that are present in the image.