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.
%0 Journal Article
%1 Luo2005
%A Luo, Jiebo
%A Savakis, Andreas E.
%A Singhal, Amit
%D 2005
%J Pattern Recognition
%K Semantic image understanding
%N 6
%P 919 - 934
%R DOI: 10.1016/j.patcog.2004.11.001
%T A Bayesian network-based framework for semantic image understanding
%U http://www.sciencedirect.com/science/article/B6V14-4FCSDM1-2/2/7d17828bd80862b826e09b52125571e2
%V 38
%X 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.
@article{Luo2005,
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.},
added-at = {2009-09-12T19:19:34.000+0200},
author = {Luo, Jiebo and Savakis, Andreas E. and Singhal, Amit},
biburl = {https://www.bibsonomy.org/bibtex/2d6c20cfaf7fab05a6e9f2ba515254bd9/mozaher},
doi = {DOI: 10.1016/j.patcog.2004.11.001},
file = {:Luo2005.pdf:PDF},
interhash = {d57ccc165da71252ad70dfe76d60f0a0},
intrahash = {d6c20cfaf7fab05a6e9f2ba515254bd9},
issn = {0031-3203},
journal = {Pattern Recognition},
keywords = {Semantic image understanding},
note = {Image Understanding for Photographs},
number = 6,
owner = {Mozaherul Hoque},
pages = {919 - 934},
timestamp = {2009-09-12T19:19:41.000+0200},
title = {A Bayesian network-based framework for semantic image understanding},
url = {http://www.sciencedirect.com/science/article/B6V14-4FCSDM1-2/2/7d17828bd80862b826e09b52125571e2},
volume = 38,
year = 2005
}