Approach to invariant object recognition on grey-level images by exploiting neural network models

摘要

A model of a neural network system for object recognition in grey-level images that is invariant with respect to position, rotation, and scale i5 developed. The model is based on the theory of D.Noton and L.Stark [6] and on the concept of Smart Sensing [2]. A method for visual image invariant representation is proposed. The method allows to transform primary features into invariant ones which can be used as input signals for a classical neural network classifier of the high-level structure of the recognizing system.