A Bayesian network-based framework for semantic image understanding

Authors:
Jiebo Luo;Andreas E. Savakis;Amit Singhal
Affiliations:
Research and Development Laboratories, Eastman Kodak Company, 1850 Dewey Ave., Rochester, NY 14650-1816, USA;Department of Computer Engineering, Rochester Institute of Technology, 83 Lomb Memorial Dr., Rochester, NY 14623, USA;Research and Development Laboratories, Eastman Kodak Company, 1850 Dewey Ave., Rochester, NY 14650-1816, USA
Venue:
Pattern Recognition
Year:
2005

Citing 19
Cited 21

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Applying Bayesian networks to information retrieval

Communications of the ACM
Using hidden nodes in Bayesian networks

Artificial Intelligence
The sensitivity of belief networks to imprecise probabilities: an experimental investigation

Artificial Intelligence - Special volume on empirical methods
Neural networks and fuzzy data fusion. Application to an online and realtime vehicle detection system

Pattern Recognition Letters
Image classification and querying using composite region templates

Computer Vision and Image Understanding - Special issue on content-based access for image and video libraries
Modeling parameter space behavior of vision systems using Bayesian networks

Computer Vision and Image Understanding
Content-Based Image Retrieval at the End of the Early Years

IEEE Transactions on Pattern Analysis and Machine Intelligence
Sensor and Data Fusion Concepts and Applications

Sensor and Data Fusion Concepts and Applications
Computer Vision

Computer Vision
Indoor-Outdoor Image Classification

CAIVD '98 Proceedings of the 1998 International Workshop on Content-Based Access of Image and Video Databases (CAIVD '98)
Content-Based Ima e Orientation Detection with Support Vector Machines

CBAIVL '01 Proceedings of the IEEE Workshop on Content-based Access of Image and Video Libraries (CBAIVL'01)
Configuration based scene classification and image indexing

CVPR '97 Proceedings of the 1997 Conference on Computer Vision and Pattern Recognition (CVPR '97)
A Computationally Efficient Approach to Indoor/Outdoor Scene Classification

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 4 - Volume 4
Context and configuration-based scene classification

Context and configuration-based scene classification
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
Content-Based Hierarchical Classification of Vacation Images

ICMCS '99 Proceedings of the IEEE International Conference on Multimedia Computing and Systems - Volume 2
Operations for learning with graphical models

Journal of Artificial Intelligence Research
Automated event clustering and quality screening of consumer pictures for digital albuming

IEEE Transactions on Multimedia

Building and tracking hierarchical geographical & temporal partitions for image collection management on mobile devices

Proceedings of the 13th annual ACM international conference on Multimedia
Detecting Interesting Regions in Photographs --- How Metadata Can Help

PCM '08 Proceedings of the 9th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
An Evidence-Driven Probabilistic Inference Framework for Semantic Image Understanding

MLDM '09 Proceedings of the 6th International Conference on Machine Learning and Data Mining in Pattern Recognition
Incorporating camera metadata for attended region detection and consumer photo classification

MM '09 Proceedings of the 17th ACM international conference on Multimedia
Event classification in personal image collections

ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Exploit camera metadata for enhancing interesting region detection and photo retrieval

Multimedia Tools and Applications
Hidden-concept driven image decomposition towards semi-supervised multi-label image annotation

Proceedings of the First International Conference on Internet Multimedia Computing and Service
Beyond pixels: Exploiting camera metadata for photo classification

Pattern Recognition
Semantic modeling of natural scenes based on contextual Bayesian networks

Pattern Recognition
Semantics extraction from images

Knowledge-driven multimedia information extraction and ontology evolution
Review: Bayesian networks in environmental modelling

Environmental Modelling & Software
Context-Based scene recognition using bayesian networks with scale-invariant feature transform

ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Interactive learning of scene context extractor using combination of bayesian network and logic network

ACIVS'06 Proceedings of the 8th international conference on Advanced Concepts For Intelligent Vision Systems
Image interpretation by combining ontologies and bayesian networks

SETN'12 Proceedings of the 7th Hellenic conference on Artificial Intelligence: theories and applications
Training inter-related classifiers for automatic image classification and annotation

Pattern Recognition
Variational learning of a Dirichlet process of generalized Dirichlet distributions for simultaneous clustering and feature selection

Pattern Recognition
Applying Bayesian Network Techniques to Prioritize Lean Six Sigma Efforts

International Journal of Strategic Decision Sciences
Image retrieval based on high level concept detection and semantic labelling

Intelligent Decision Technologies
Scene classification using multi-resolution low-level feature combination

Neurocomputing
Support vector description of clusters for content-based image annotation

Pattern Recognition
Non-Gaussian Data Clustering via Expectation Propagation Learning of Finite Dirichlet Mixture Models and Applications

Neural Processing Letters

Quantified Score

Hi-index	0.01

Visualization

Abstract

Current research in content-based semantic image understanding is largely confined to exemplar-based approaches built on low-level feature extraction and classification. The ability to extract both low-level and semantic features and perform knowledge integration of different types of features is expected to raise semantic image understanding to a new level. Belief networks, or Bayesian networks (BN), have proven to be an effective knowledge representation and inference engine in artificial intelligence and expert systems research. Their effectiveness is due to the ability to explicitly integrate domain knowledge in the network structure and to reduce a joint probability distribution to conditional independence relationships. In this paper, we present a general-purpose knowledge integration framework that employs BN in integrating both low-level and semantic features. The efficacy of this framework is demonstrated via three applications involving semantic understanding of pictorial images. The first application aims at detecting main photographic subjects in an image, the second aims at selecting the most appealing image in an event, and the third aims at classifying images into indoor or outdoor scenes. With these diverse examples, we demonstrate that effective inference engines can be built within this powerful and flexible framework according to specific domain knowledge and available training data to solve inherently uncertain vision problems.