Paper Search Console

Home Search Page About Contact

Journal Title

Title of Journal: Machine Vision and Applications

Search In Journal Title:

Abbravation: Machine Vision and Applications

Search In Journal Abbravation:

Publisher

Springer-Verlag

Search In Publisher:

DOI

10.1007/s11557-009-0641-1

Search In DOI:

ISSN

1432-1769

Search In ISSN:
Search In Title Of Papers:

Qualitative partbased models in contentbased ima

Authors: GuillaumeAlexandre Bilodeau Robert Bergevin
Publish Date: 2007/01/10
Volume: 18, Issue: 5, Pages: 275-287
PDF Link

Abstract

A qualitative volumetric partbased model is proposed to improve the categorical invariance and viewpoint invariance in contentbased image retrieval and a novel twostep partcategorization method is presented to build it The method consists first in transforming parts extracted from a segmented contour primitive map and then categorizing the transformed parts using interpretation rules The first step allows noisy extracted parts to be transformed to the domain of a simple classifier The second step computes features of the transformed parts for categorization Contentbased image retrieval experiments using real images of complex multipart objects confirm that a model built from the categorized parts improves both the categorical invariance and the viewpoint invariance It does so by directly addressing the fundamental limits of lowlevel models


Keywords:

References


.
Search In Abstract Of Papers:
Other Papers In This Journal:


Search Result: