A visual pathway for shape-based invariant classification of gray scale images

Authors:
Konstantinos A. Raftopoulos;Nikolaos Papadakis;Klimis Ntalianis;Stefanos Kollias
Affiliations:
(Correspd. Tel.: +30 210 772 2521/ Fax: +30 210 772 2492/ raftop@image.ntua.gr) Image, Video and Multimedia Sys. Lab., Natnl. Tech. Univ. of Athens, Sch. of Elec. and Comp. Eng., Comp. Sci. Div., ...;Image, Video and Multimedia Systems Laboratory, Natnl. Tech. Univ. of Athens, Sch. of Elec. and Comp. Eng., Comp. Sci. Div., Iroon Polytexneiou 9, 15780 Zografou, Greece, Electrical Engineering Bu ...;Image, Video and Multimedia Systems Laboratory, Natnl. Tech. Univ. of Athens, Sch. of Elec. and Comp. Eng., Comp. Sci. Div., Iroon Polytexneiou 9, 15780 Zografou, Greece, Electrical Engineering Bu ...;Image, Video and Multimedia Systems Laboratory, Natnl. Tech. Univ. of Athens, Sch. of Elec. and Comp. Eng., Comp. Sci. Div., Iroon Polytexneiou 9, 15780 Zografou, Greece, Electrical Engineering Bu ...
Venue:
Integrated Computer-Aided Engineering - Artificial Neural Networks
Year:
2007

Citing 11
Cited 5

The Curvature Primal Sketch

IEEE Transactions on Pattern Analysis and Machine Intelligence
Scale-Based Description and Recognition of Planar Curves and Two-Dimensional Shapes

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Theory of Multiscale, Curvature-Based Shape Representation for Planar Curves

IEEE Transactions on Pattern Analysis and Machine Intelligence
Machine vision

Machine vision
Shape representation and recognition from multiscale curvature

Computer Vision and Image Understanding
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Fast correspondence-based system for shape retrieval

Pattern Recognition Letters
Visual pathways for detection of landmark points

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
Retrieval by shape similarity with perceptual distance andeffective indexing

IEEE Transactions on Multimedia
Snakes, shapes, and gradient vector flow

IEEE Transactions on Image Processing
Multiscale curvature-based shape representation using B-spline wavelets

IEEE Transactions on Image Processing

A probabilistic neural network for earthquake magnitude prediction

Neural Networks
An efficient fingerprint image compression technique based on wave atoms decomposition and multistage vector quantization

Integrated Computer-Aided Engineering
Spectral shape descriptor using spherical harmonics

Integrated Computer-Aided Engineering
Visual pathways for shape abstraction

ICANN'11 Proceedings of the 21th international conference on Artificial neural networks - Volume Part I
Multi-object segmentation approach based on topological derivative and level set method

Integrated Computer-Aided Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

Inspired by the rotated orientation specific receptive fields of the simple neurons that were discovered by Hubel and Wiesel we describe a multi-layered neural architecture for calculating the local curvature at each point of a planar shape without extracting the underlying contour. Our architecture resembles the visual pathway of primates as we demonstrate how the rotated orientation specific receptive fields of the simple neurons can perform local curvature calculation of the planar shape that is projected on the retina of the eye. We then use the same method to encode planar curvature into the intensity of gray scale images and we demonstrate the effectiveness of this encoding by proposing a shape-based triple correlation invariant image classification scheme. We present experimental results illustrating that by encoding planar curvature into the intensity values we improve the recognition capability of multi layered neural network classifiers without imposing additional complexity to the learning process.