Authors: | Ntalianis, Klimis Raftopoulos, Konstantinos A. Papadakis, Nikos Kollias, Stefanos |
Issue Date: | 1-Jan-2007 |
Journal: | Integrated Computer-Aided Engineering |
Volume: | 14 |
Issue: | 4 |
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. |
ISSN: | 1069-2509 |
DOI: | 10.3233/ica-2007-14407 |
URI: | https://uniwacris.uniwa.gr/handle/3000/2738 |
Type: | Article |
Department: | Department of Business Administration |
School: | School of Administrative, Economics and Social Sciences |
Affiliation: | University of West Attica (UNIWA) |
Appears in Collections: | Articles / Άρθρα |
CORE Recommender
SCOPUSTM
Citations
10
checked on Sep 6, 2024
Page view(s)
14
checked on Sep 11, 2024
Google ScholarTM
Check
Altmetric
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.