Recognition of 2-d shapes inspired by the human visual system

Abstract

This paper presents a new method suitable for shape recognition, inspired by the Primary Visual Cortex of the Human Visual System. It extracts a description for 2-dimensional shapes with a closed contour, regardless of their size, rotation and position, with low computational cost. The paper introduces a new computational approach to the modeling of the hypercolumns of the Primary Visual Cortex, which requires significantly less computational burden and which is highly parallel. A new shape descriptor based on the relative angles of an object is also proposed. It produces close results for different shapes of the same object, it is proportion-flexible and it can identify distorted shapes correctly. Experimental results prove that the method is adequate for shape-based image retrieval and classification, as well as for efficiently storage of edges and line drawings.