Semantic Scene Classification for Image Annotation and Retrieval

Authors:
Özge Çavuş;Selim Aksoy
Affiliations:
Department of Computer Engineering, Bilkent University, Ankara, Turkey 06800;Department of Computer Engineering, Bilkent University, Ankara, Turkey 06800
Venue:
SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Year:
2008

Citing 6
Cited 2

Consistent Line Clusters for Building Recognition in CBIR

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Support Vector Data Description

Machine Learning
A Generative/Discriminative Learning Algorithm for Image Classification

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Robust Scene Categorization by Learning Image Statistics in Context

CVPRW '06 Proceedings of the 2006 Conference on Computer Vision and Pattern Recognition Workshop
Semantic Modeling of Natural Scenes for Content-Based Image Retrieval

International Journal of Computer Vision
A Thousand Words in a Scene

IEEE Transactions on Pattern Analysis and Machine Intelligence

Automatic Image Annotation Using Color K-Means Clustering

IVIC '09 Proceedings of the 1st International Visual Informatics Conference on Visual Informatics: Bridging Research and Practice
A review on automatic image annotation techniques

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe an annotation and retrieval framework that uses a semantic image representation by contextual modeling of images using occurrence probabilities of concepts and objects. First, images are segmented into regions using clustering of color features and line structures. Next, each image is modeled using the histogram of the types of its regions, and Bayesian classifiers are used to obtain the occurrence probabilities of concepts and objects using these histograms. Given the observation that a single class with the highest probability is not sufficient to model image content in an unconstrained data set with a large number of semantically overlapping classes, we use the concept/object probabilities as a new representation, and perform retrieval in the semantic space for further improvement of the categorization accuracy. Experiments on the TRECVID and Corel data sets show good performance.