Automatic generation of semantic metadata describing spatial relations
is highly desirable for image digital libraries. Relative spatial
relations between objects in an image convey important information
about the image. Because the perception of spatial relations is subjective,
we propose a novel framework for automatic metadata generation based
on fuzzy k-NN classification that generates fuzzy semantic metadata
describing spatial relations between objects in an image. For each
pair of objects of interest, the corresponding R-Histogram is computed
and used as input for a set of fuzzy k-NN classifiers. The R-Histogram
is a quantitative representation of spatial relations between two
objects. The outputs of the classifiers are soft class labels for
each of the following eight spatial relations: 1) LEFT OF, 2) RIGHT
OF, 3) ABOVE, 4) BELOW, 5) NEAR, 6) FAR, 7) INSIDE, 8) OUTSIDE. Because
the classifier-training stage involves annotating the training images
manually, it is desirable to use as few training images as possible.
To address this issue, we applied existing prototype selection techniques
and also devised two new extensions. We evaluated the performance
of different fuzzy k-NN algorithms and prototype selection algorithms
empirically on both synthetic and real images. Preliminary experimental
results show that our system is able to obtain good annotation accuracy
(92%-98% on synthetic images and 82%-93% on real images) using only
a small training set (4-5 images).
%0 Conference Paper
%1 Wang2004
%A Wang, Yuhang
%A Makedon, Fillia
%A Ford, James
%A Shen, Li
%A Goldin, Dina
%B Digital Libraries, 2004. Proceedings of the 2004 Joint ACM/IEEE Conference
on
%D 2004
%K (artificial R-histogram, Web, analysis, classification, classifier-training data, databases digital fuzzy image intelligence), k-NN learning libraries, library, meta metadata, nets, neural pattern relations retrieval, semantic spatial stage, statistical visual
%P 202-211
%R 10.1109/JCDL.2004.1336121
%T Generating fuzzy semantic metadata describing spatial relations from
images using the R-histogram
%X Automatic generation of semantic metadata describing spatial relations
is highly desirable for image digital libraries. Relative spatial
relations between objects in an image convey important information
about the image. Because the perception of spatial relations is subjective,
we propose a novel framework for automatic metadata generation based
on fuzzy k-NN classification that generates fuzzy semantic metadata
describing spatial relations between objects in an image. For each
pair of objects of interest, the corresponding R-Histogram is computed
and used as input for a set of fuzzy k-NN classifiers. The R-Histogram
is a quantitative representation of spatial relations between two
objects. The outputs of the classifiers are soft class labels for
each of the following eight spatial relations: 1) LEFT OF, 2) RIGHT
OF, 3) ABOVE, 4) BELOW, 5) NEAR, 6) FAR, 7) INSIDE, 8) OUTSIDE. Because
the classifier-training stage involves annotating the training images
manually, it is desirable to use as few training images as possible.
To address this issue, we applied existing prototype selection techniques
and also devised two new extensions. We evaluated the performance
of different fuzzy k-NN algorithms and prototype selection algorithms
empirically on both synthetic and real images. Preliminary experimental
results show that our system is able to obtain good annotation accuracy
(92%-98% on synthetic images and 82%-93% on real images) using only
a small training set (4-5 images).
@inproceedings{Wang2004,
abstract = { Automatic generation of semantic metadata describing spatial relations
is highly desirable for image digital libraries. Relative spatial
relations between objects in an image convey important information
about the image. Because the perception of spatial relations is subjective,
we propose a novel framework for automatic metadata generation based
on fuzzy k-NN classification that generates fuzzy semantic metadata
describing spatial relations between objects in an image. For each
pair of objects of interest, the corresponding R-Histogram is computed
and used as input for a set of fuzzy k-NN classifiers. The R-Histogram
is a quantitative representation of spatial relations between two
objects. The outputs of the classifiers are soft class labels for
each of the following eight spatial relations: 1) LEFT OF, 2) RIGHT
OF, 3) ABOVE, 4) BELOW, 5) NEAR, 6) FAR, 7) INSIDE, 8) OUTSIDE. Because
the classifier-training stage involves annotating the training images
manually, it is desirable to use as few training images as possible.
To address this issue, we applied existing prototype selection techniques
and also devised two new extensions. We evaluated the performance
of different fuzzy k-NN algorithms and prototype selection algorithms
empirically on both synthetic and real images. Preliminary experimental
results show that our system is able to obtain good annotation accuracy
(92%-98% on synthetic images and 82%-93% on real images) using only
a small training set (4-5 images).},
added-at = {2009-09-12T19:19:34.000+0200},
author = {Wang, Yuhang and Makedon, Fillia and Ford, James and Shen, Li and Goldin, Dina},
biburl = {https://www.bibsonomy.org/bibtex/27aac61f40a6b0dbd0058a2593df46239/mozaher},
booktitle = {Digital Libraries, 2004. Proceedings of the 2004 Joint ACM/IEEE Conference
on},
doi = {10.1109/JCDL.2004.1336121},
file = {:Wang2004.pdf:PDF},
interhash = {42db84dc85debb46b1624e5ff21efcd8},
intrahash = {7aac61f40a6b0dbd0058a2593df46239},
keywords = {(artificial R-histogram, Web, analysis, classification, classifier-training data, databases digital fuzzy image intelligence), k-NN learning libraries, library, meta metadata, nets, neural pattern relations retrieval, semantic spatial stage, statistical visual},
month = {June},
owner = {Mozaher},
pages = { 202-211},
timestamp = {2009-09-12T19:19:43.000+0200},
title = {Generating fuzzy semantic metadata describing spatial relations from
images using the R-histogram},
year = 2004
}