Abstract 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-of-the-art feature, SIFT, for feature-based object recognition. The experimental results validate the robustness of the proposed perceptual feature in object recognition.
Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature
Computer Vision – ACCV 2006 ; 2 ; 305-314
Lecture Notes in Computer Science ; 3852 , 2
2006-01-01
10 pages
Article/Chapter (Book)
Electronic Resource
English
Recognition Rate , Edge Density , Visual Part , Perceptual Feature , Edge Orientation Computer Science , Image Processing and Computer Vision , Computer Imaging, Vision, Pattern Recognition and Graphics , Pattern Recognition , Artificial Intelligence (incl. Robotics) , Algorithm Analysis and Problem Complexity
Biologically Motivated Perceptual Feature: Generalized Robust Invariant Feature
British Library Conference Proceedings | 2006
|A Biologically-Motivated Robot Eye System
British Library Conference Proceedings | 1994
|A Biologically Motivated Flight Control System for PAVs
Trans Tech Publications | 2013
|British Library Online Contents | 2014
|