The Classification of Fragments of Objects by the Fourier Mask Digital System

Abstract

The automation process of the pattern recognition for fragments of objects is a challenge to humanity. For humans it is relatively easy to classify a fragment of some object even if it is isolate and maybe this identification could be more complicated if it is partially overlapped by other object. However, the emulation of the functions of the human eye and brain by a computer is not a trivial issue. This paper presents a pattern recognition digital system based on Fourier binary rings mask to classify fragments of objects. The digital system is invariant to position and rotation, it is robust in the classification of images that have noise and non-homogenous illumination, moreover it classifies images that present an occlusion or elimination until the 15% of the area of the object.