Edge detection using neural network arbitration

A human observer is able to recognise and describe most parts of an object by its contour, if this is properly traced and reflects the shape of the object itself. With a machine vision system this recognition task has been approached using a similar technique. This prompted the development of many d...

Full description

Bibliographic Details
Main Author: Ramalho, Mário António da Silva Neves
Format: Thesis (University of Nottingham only)
Language:English
Published: 1996
Subjects:
Online Access:https://eprints.nottingham.ac.uk/12883/
_version_ 1848791599822143488
author Ramalho, Mário António da Silva Neves
author_facet Ramalho, Mário António da Silva Neves
author_sort Ramalho, Mário António da Silva Neves
building Nottingham Research Data Repository
collection Online Access
description A human observer is able to recognise and describe most parts of an object by its contour, if this is properly traced and reflects the shape of the object itself. With a machine vision system this recognition task has been approached using a similar technique. This prompted the development of many diverse edge detection algorithms. The work described in this thesis is based on the visual observation that edge maps produced by different algorithms, as the image degrades. Display different properties of the original image. Our proposed objective is to try and improve the edge map through the arbitration between edge maps produced by diverse (in nature, approach and performance) edge detection algorithms. As image processing tools are repetitively applied to similar images we believe the objective can be achieved by a learning process based on sample images. It is shown that such an approach is feasible, using an artificial neural network to perform the arbitration. This is taught from sets extracted from sample images. The arbitration system is implemented upon a parallel processing platform. The performance of the system is presented through examples of diverse types of image. Comparisons with a neural network edge detector (also developed within this thesis) and conventional edge detectors show that the proposed system presents significant advantages.
first_indexed 2025-11-14T18:31:05Z
format Thesis (University of Nottingham only)
id nottingham-12883
institution University of Nottingham Malaysia Campus
institution_category Local University
language English
last_indexed 2025-11-14T18:31:05Z
publishDate 1996
recordtype eprints
repository_type Digital Repository
spelling nottingham-128832025-02-28T11:21:54Z https://eprints.nottingham.ac.uk/12883/ Edge detection using neural network arbitration Ramalho, Mário António da Silva Neves A human observer is able to recognise and describe most parts of an object by its contour, if this is properly traced and reflects the shape of the object itself. With a machine vision system this recognition task has been approached using a similar technique. This prompted the development of many diverse edge detection algorithms. The work described in this thesis is based on the visual observation that edge maps produced by different algorithms, as the image degrades. Display different properties of the original image. Our proposed objective is to try and improve the edge map through the arbitration between edge maps produced by diverse (in nature, approach and performance) edge detection algorithms. As image processing tools are repetitively applied to similar images we believe the objective can be achieved by a learning process based on sample images. It is shown that such an approach is feasible, using an artificial neural network to perform the arbitration. This is taught from sets extracted from sample images. The arbitration system is implemented upon a parallel processing platform. The performance of the system is presented through examples of diverse types of image. Comparisons with a neural network edge detector (also developed within this thesis) and conventional edge detectors show that the proposed system presents significant advantages. 1996 Thesis (University of Nottingham only) NonPeerReviewed application/pdf en arr https://eprints.nottingham.ac.uk/12883/1/318633.pdf Ramalho, Mário António da Silva Neves (1996) Edge detection using neural network arbitration. PhD thesis, University of Nottingham. Image processing Pattern recognition systems Pattern perception
spellingShingle Image processing
Pattern recognition systems
Pattern perception
Ramalho, Mário António da Silva Neves
Edge detection using neural network arbitration
title Edge detection using neural network arbitration
title_full Edge detection using neural network arbitration
title_fullStr Edge detection using neural network arbitration
title_full_unstemmed Edge detection using neural network arbitration
title_short Edge detection using neural network arbitration
title_sort edge detection using neural network arbitration
topic Image processing
Pattern recognition systems
Pattern perception
url https://eprints.nottingham.ac.uk/12883/