Computational Model for Rotation-Invariant Perception

Abstract

Visual perception of rotation is one of important functions of processing information in the visual pathway. To simulate the mechanism, we propose a model for perception of rotation. First, we briefly introduce the rotation-invariant basis functions learned from natural scenes using independent component analysis (ICA). We used these basis functions to construct the perceptual model. By using the correlation coefficients of two neural responses as the measure of rotation-invariance, our model can perform the task of perception of rotating angles. Computer simulation results show that the present model is able to perceive rotation- invariance and successfully perceive the relative angles of rotating patches.