L’outil de licence Creative Commons du formulaire de soumission ne fonctionne pas actuellement. Pour ajouter une licence CC à votre thèse ou publication, contactez ruor@uottawa.ca après le dépôt. -- The Creative Commons licence tool in the submission form is currently unavailable. To apply a CC licence to your thesis or publication, contact ruor@uottawa.ca after the deposit.

Image segment processing for analysis and visualization

En cours de chargement...
Vignette d'image

Date

Nom de la revue

ISSN de la revue

Titre du volume

Éditeur

University of Ottawa (Canada)

Résumé

This thesis is a study of the probabilistic relationship between objects in an image and image appearance. We give a hierarchical, probabilistic criterion for the Bayesian segmentation of photographic images. We validate the segmentation against the Berkeley Segmentation Data Set, where human subjects were asked to partition digital images into segments each representing a 'distinguished thing'. We show that there exists a strong dependency between the hierarchical segmentation criterion, based on our assumptions about the visual appearance of objects, and the distribution of ground truth data. That is, if two pixels have similar visual properties then they will often have the same ground truth state. Segmentation accuracy is quantified by measuring the information cross-entropy between the ground truth probability distribution and an estimate obtained from the segmentation. We consider the proposed method for estimating joint ground truth probability to be an important tool for future image analysis and visualization work.

Description

Mots-clés

Citation

Source: Masters Abstracts International, Volume: 47-04, page: 2234.

Approbation

Évaluation

Complété par

Référencé par