An Evidence-Driven Probabilistic Inference Framework for Semantic Image Understanding

Authors:
Spiros Nikolopoulos;Georgios Th. Papadopoulos;Ioannis Kompatsiaris;Ioannis Patras
Affiliations:
Informatics and Telematics Institute, CERTH, Thessaloniki, Greece;Informatics and Telematics Institute, CERTH, Thessaloniki, Greece;Informatics and Telematics Institute, CERTH, Thessaloniki, Greece;School of Electronic Engineering and Computer Science, Queen Mary University of London, London, UK E1 4NS
Venue:
MLDM '09 Proceedings of the 6th International Conference on Machine Learning and Data Mining in Pattern Recognition
Year:
2009

Citing 13
Cited 0

Fusion, propagation, and structuring in belief networks

Artificial Intelligence
Local computations with probabilities on graphical structures and their application to expert systems

Readings in uncertain reasoning
Object Recognition as Machine Translation: Learning a Lexicon for a Fixed Image Vocabulary

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part IV
Bayesian Network Structure Learning and Inference in Indoor vs. Outdoor Image Classification

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Ontological inference for image and video analysis

Machine Vision and Applications
Combining global and local classifiers with Bayesian network

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
The Semantic Web Vision: Where Are We?

IEEE Intelligent Systems
Combining global and local information for knowledge-assisted image analysis and classification

EURASIP Journal on Advances in Signal Processing
A Bayesian network-based framework for semantic image understanding

Pattern Recognition
Description logics in ontology applications

TABLEAUX'05 Proceedings of the 14th international conference on Automated Reasoning with Analytic Tableaux and Related Methods
A probabilistic framework for semantic video indexing, filtering,and retrieval

IEEE Transactions on Multimedia
Color and texture descriptors

IEEE Transactions on Circuits and Systems for Video Technology
Semantic Image Segmentation and Object Labeling

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

This work presents an image analysis framework driven by emerging evidence and constrained by the semantics expressed in an ontology. Human perception, apart from visual stimulus and pattern recognition, relies also on general knowledge and application context for understanding visual content in conceptual terms. Our work is an attempt to imitate this behavior by devising an evidence driven probabilistic inference framework using ontologies and bayesian networks. Experiments conducted for two different image analysis tasks showed improvement in performance, compared to the case where computer vision techniques act isolated from any type of knowledge or context.