Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature

In this paper, we present a new, biologically inspired perceptual feature to solve the selectivity and invariance issue in object recognition. Based on the recent findings in neuronal and cognitive mechanisms in human visual systems, we develop a computationally efficient model. An effective form of a visual part detector combines a radial symmetry detector with a corner-like structure detector. A general context descriptor encodes edge orientation, edge density, and hue information using a localized receptive field histogram. We compare the proposed perceptual feature (G-RIF: generalized robust invariant feature) with the state-ofthe-art feature, SIFT, for feature-based object recognition. The experimental results validate the robustness of the proposed perceptual feature in object recognition.