![](bg7.png)
to conclude that this fire could be the result of
burning in a paddy field or a nearby primary forest.
Thus, with two attributes such as length and area,
each having five possible fuzzy labels, it is possible
to generate 5
2
+1 descriptions. The GA has searched
for an optimal solution among these descriptions
within a very short time.
5 CONCLUSIONS AND FUTURE
WORK
This paper has presented a new approach to
describing patterns in images using linguistic
summaries that use fuzzy labels. A genetic algorithm
technique has been employed to evolve the most
suitable linguistic summary that describes each
object/pattern in the database. Image mining is used
to extract unusual patterns such as fire in the same
geographic area from images collected over two
different dates. This method can be extended to an
array of images of the same geographic area, taken
over a period of several years, to describe many other
interesting and unusual patterns that emerge over
time.
Some directions for future work include:
1. Development and implementation of
clustering algorithms in order to evaluate
automatically the additional information
attribute in the tables. Currently
pre-segmented images are used.
2. Development of a user friendly tool with
graphical interface to ease the task of
extracting and calculating feature descriptors
such as area, length, gray level intensity,
colour etc., stored in the tables. Currently,
both MATLAB and ENVI are required in
order to populate the tables. Each has its own
limitations.
Acknowledgment: The authors wish to acknowledge
and express gratitude to Dr. B. S. D. Sagar for his
valuable advice in the domain of remote-sensing.
REFERENCES
Buckles, B.P, Petry, F.E, Prabhu, D, Lybanon,M., 1996.
Mesoscale Feature Labeling from Satellite Images. In
Genetic Algorithms for Pattern Recognition, eds.
Sankar K.Pal, Paul P. Wang, CRC Press, pp. 167-175.
Filho, J.L.R, Treleaven, P.C, Alippi, C., 1994. Genetic
Algorithm programming environments. In IEEE
Computer, pp.28-43.
Goodman, E,D., 1996. An Introduction to Galopps-the
Genetic ALgorithm Optimized for Portability and
Parallelism System(Release 3.2). Technical Report No.
96-07-01, Genetic Algorithms Research and
Applications Group, Michigan State University.
Kacprzyk, J , Ziolkowski, A., 1986. Database queries with
fuzzy linguistic quantifers. In IEEE Transactions on
Systems, Man and Cybernetics, pp. 474-479.
Mendel, J.M., 2001. Uncertain Rule-Based Fuzzy Logic
Systems: Introduction and New Directions, Prentice
Hall.
Motro, A., 1994 . Intensional Answers to Database Queries.
In IEEE Transactions on knowledge and data
engineering, pp. 444-454.
Nair, H, George, R, Srikanth, R, Warsi, N.A., 1994.
Intensional Answering in Databases-A Fuzzy Logic
Approach. In Proceedings of Joint Conference on
Information Systems.
Nair, H., 2003. Developing linguistic summaries of
patterns from mined images. In Proceedings of Fifth
International Conference on Advances in Pattern
Recognition, pp. 261-267.
Research Systems Inc.,1997. ENVI Version 3.0 User’s
Guide. Better Solutions Consulting.
Smith, R.E, Goldberg, D.E, Earickson, J.A., 1994.
SGA-C:A C-language implementation of a Simple
Genetic Algorithm. TCGA Report No.91002.
The Mathworks Inc.,1997. MATLAB Image Processing
Toolbox User's Guide.
Thuraisingham, B., 2001. Managing and Mining
Multimedia Databases, CRC Press.
Yager, R.R., 1991. On Linguistic Summaries of Data. In
Knowledge Discovery In Databases, eds. Gregory
Piatetsky-Shapiro and William J. Frawley , AAAI Press,
pp.347-363.
Zaine, O.R, Han, J, Li, Z.N, Hon, J., 1998. Mining
multimedia data. In CASCON'98, Meeting of Minds.
LINGUISTIC DESCRIPTION OF PATTERNS FROM MINED IMAGES
83