Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/54196
Title: Novel neural network models for computing homothetic invariances: an image algebra notation
Authors: Suárez Araujo, Carmen Paz 
UNESCO Clasification: 120304 Inteligencia artificial
Keywords: Morphological neural networks
image algebra
Invariant perception
Homothetical invariances perception
Issue Date: 1997
Publisher: 0924-9907
Journal: Journal of Mathematical Imaging and Vision 
Abstract: In this paper we propose a theoretical approach toinvariant perception. Invariant perception is an importantaspect in both natural and artificial perception systems, and itremains an important unsolved problem in heuristically basedpattern recognition. Our approach is based on a general theoryof neural networks and studies of invariant perception by thecortex. The neural structures that we propose uphold both thearchitecture and functionality of the cortex as currentlyunderstood. The formulation of the proposed neural structuresis in the language of image algebra, a mathematical environmentfor expressing image processing algorithms. Thus, an additionalbenefit of our study is the implication that image algebraprovides an excellent environment for expressing and developingartificial perception systems. The focus of our study is oninvariances that are expressible in terms of affinetransformations, specifically, homothetic transformations. Ourdiscussion will include both one-dimensional andtwo-dimensional signal patterns. The main contribution of thispaper is the formulation of several novel morphological neuralnetworks that compute homothetic auditory and visualinvariances. With respect to the latter, we employ the theoryand trends of currently popular artificial vision systems.
URI: http://hdl.handle.net/10553/54196
ISSN: 0924-9907
DOI: https://doi.org/10.1023/A:1008218108171
Source: Journal of Mathematical Imaging and Vision [ISSN 0924-9907], v. 7, p. 69-83
Appears in Collections:Artículos
Show full item record

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.