Interacting Cortical Filters for Object Recognition

摘要

It is shown how cortical filters can be used for image analysis and objectrecognition. Similarly to previous work in this area, we compute functional inner products of a two-dimensional input signal (image) with a set of two-dimensional Gabor functions which fit the receptive fields of simple cells in the primary visual cortex of mammals. We propose a method in which these inner products become the subject of thresholding, orientation competition and lateral inhibition. Each of the resulting cortical images contains only edge lines of a particular orientation and a particular light-to-dark transition direction. In this way, the information which is present in the original image is split in different channels and we show how this splitting can be used for object recognition. Each cortical image is reduced to a single number so that a set of cortical images that emanate from the same input image is reduced to a set of descriptors of the input image which are robust for translations of an object in the visual field. Multi-scale resolution and dynamic programming are used to compensate for size variations, rotations and non-topologic form differences. The method discriminates between simple geometrical figures, e.g. polygons with different numbers of edges, with reliability of 100% and a recognition rate of 99% has been achieved when the method was applied to a large database of face images.