Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
SVM-based Relevance Feedback in Image Retrieval using Invariant Feature Histograms
 

Summary: SVM-based Relevance Feedback in Image Retrieval
using Invariant Feature Histograms
Lokesh Setia, Julia Ick, Hans Burkhardt
Institute of Computer Science
Albert-Ludwigs-University Freiburg
79110 Freiburg im Breisgau, Germany
Email: {setia, ick, burkhardt} @informatik.uni-freiburg.de
Abstract-- Relevance Feedback is an interesting procedure
to improve the performance of Content-Based Image Retrieval
systems even when using low-level features alone. In this work
we compare the efficiency of one class and two class Support
Vector Machines in content-based image retrieval using Invariant
Feature Histograms. We describe our methodology of performing
Relevance Feedback in both cases and report encouraging results
on a subset of MPEG-7 content dataset.
I. INTRODUCTION
Image retrieval is becoming ever more important as the
amount of available multimedia data increases. Increasing
database sizes also means that manual annotation of image
databases becomes prohibitively expensive. Manual annotation

  

Source: Albert-Ludwigs-Universität Freiburg, Institut für Informatik,, Lehrstuhls für Mustererkennung und Bildverarbeitung

 

Collections: Computer Technologies and Information Sciences