The University of Southampton
University of Southampton Institutional Repository

A dual active contour including parametric shape

A dual active contour including parametric shape
A dual active contour including parametric shape
A fundamental requirement in many computer vision systems is the ability to extract regions and feature boundaries from images. An active contour, or snake, is an energy minimising spline that is constrained by its own internal forces of continuity and curvature, whilst external forces drive it towards desired image features. The external forces are provided by the image and where appropriate, information from a higher-level process may be included. The technique is formulated as an energy minimisation problem. The minimisation process evolves an initial contour towards an appropriate feature. The snake's energy depends on its shape and location within the image. The image functional is constructed so that local minima correspond to desired features and hence the snake is attracted towards them. Typically there are many local minima in the energy function. In this situation the contour may become trapped in neighbouring edges resulting in a false boundary. Consequently an initial contour must be placed near the required feature in order to extract it successfully. This characterises the snake's strength, being able to extract many types of features from an image, at the expense of its weakness, sensitivity to the choice of the initial contour. Furthermore the contour contains no knowledge of the desired shape, and attains a shape with minimum curvature when submitted to no external forces. This reduces it efficacy in the extraction of non-convex shapes. A novel dual active contour has been developed to reduce the sensitivity to initialisation and enhance the extraction of non-convex shapes. The dual active contour integrates one contour expanding from within the feature to one contracting from outside it. This technique may be supplemented with parametric shape information to provide increased robustness. The inclusion of this global shape information biases the contour towards a target shape, enhancing the ability of the contours to distinguish unwanted image features. A method used a probabilistic shape model to integrate global shape information with the contour in a parameter space; this reduces speed, but demonstrates the increased robustness provided by the inclusion of shape information. The model-based dual active contour is directly applicable in image space as opposed to parameter space, and is developed as an extension to the idea of a dual snake. Active contour techniques have been proposed to extract an approximation to the head boundary. A conventional snake approach was used to shrink an active contour onto a face boundary, however it was shown how the contour can become caught on unwanted image features. Similarly used a contracting approach but modified the snake parameters depending on the part of the head being extracted, (hair, chin or ears). An alternative approach used an expanding active contour aiming to find an internal face boundary, targeted at face description. The choice between expanding and contracting contours concerns how to handle the upper part of the face and whether to extract the lower hairline or the top of the head. Our technique has been developed to robustly extract head boundaries in an image. By virtue of its configuration the dual contour provides two contours, an inner face contour and an external face contour.
University of Southampton
Gunn, S.R.
306af9b3-a7fa-4381-baf9-5d6a6ec89868
Nixon, M.S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12
Gunn, S.R.
306af9b3-a7fa-4381-baf9-5d6a6ec89868
Nixon, M.S.
2b5b9804-5a81-462a-82e6-92ee5fa74e12

Gunn, S.R. and Nixon, M.S. (1994) A dual active contour including parametric shape Southampton. University of Southampton

Record type: Monograph (Project Report)

Abstract

A fundamental requirement in many computer vision systems is the ability to extract regions and feature boundaries from images. An active contour, or snake, is an energy minimising spline that is constrained by its own internal forces of continuity and curvature, whilst external forces drive it towards desired image features. The external forces are provided by the image and where appropriate, information from a higher-level process may be included. The technique is formulated as an energy minimisation problem. The minimisation process evolves an initial contour towards an appropriate feature. The snake's energy depends on its shape and location within the image. The image functional is constructed so that local minima correspond to desired features and hence the snake is attracted towards them. Typically there are many local minima in the energy function. In this situation the contour may become trapped in neighbouring edges resulting in a false boundary. Consequently an initial contour must be placed near the required feature in order to extract it successfully. This characterises the snake's strength, being able to extract many types of features from an image, at the expense of its weakness, sensitivity to the choice of the initial contour. Furthermore the contour contains no knowledge of the desired shape, and attains a shape with minimum curvature when submitted to no external forces. This reduces it efficacy in the extraction of non-convex shapes. A novel dual active contour has been developed to reduce the sensitivity to initialisation and enhance the extraction of non-convex shapes. The dual active contour integrates one contour expanding from within the feature to one contracting from outside it. This technique may be supplemented with parametric shape information to provide increased robustness. The inclusion of this global shape information biases the contour towards a target shape, enhancing the ability of the contours to distinguish unwanted image features. A method used a probabilistic shape model to integrate global shape information with the contour in a parameter space; this reduces speed, but demonstrates the increased robustness provided by the inclusion of shape information. The model-based dual active contour is directly applicable in image space as opposed to parameter space, and is developed as an extension to the idea of a dual snake. Active contour techniques have been proposed to extract an approximation to the head boundary. A conventional snake approach was used to shrink an active contour onto a face boundary, however it was shown how the contour can become caught on unwanted image features. Similarly used a contracting approach but modified the snake parameters depending on the part of the head being extracted, (hair, chin or ears). An alternative approach used an expanding active contour aiming to find an internal face boundary, targeted at face description. The choice between expanding and contracting contours concerns how to handle the upper part of the face and whether to extract the lower hairline or the top of the head. Our technique has been developed to robustly extract head boundaries in an image. By virtue of its configuration the dual contour provides two contours, an inner face contour and an external face contour.

This record has no associated files available for download.

More information

Published date: 1994
Organisations: Electronic & Software Systems, Southampton Wireless Group

Identifiers

Local EPrints ID: 250093
URI: http://eprints.soton.ac.uk/id/eprint/250093
PURE UUID: 059c5d9e-5fbe-49f1-b964-6d5358dabfde
ORCID for M.S. Nixon: ORCID iD orcid.org/0000-0002-9174-5934

Catalogue record

Date deposited: 29 Oct 2001
Last modified: 11 Dec 2021 02:38

Export record

Contributors

Author: S.R. Gunn
Author: M.S. Nixon ORCID iD

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×