as in
ame
[x31
e in
nges
erent
> and
The
used
soil
was
ever,
er of
erage
pixel
n the
using
class
6. CONCLUSION
On the whole, in this study it was found that Entropy and ASM
resulted in the maximum number of distinct class pairs for all
the window sizes. However, ASM in all the three dates and all
the window sizes resulted in better feature discrimination than
Entropy. The window size of 25x25 was found to be optimal
for the current study. Cotton, Pearl millet, rice and scrub could
be separable in the first two dates. By the third date due to the
similar stages of rice, cotton and pearl millet, the backscatter
did not significantly contribute to the textural information.
Even where the number of distinct class pairs was similar
between the different texture measures under given window
sizes, it was found that ASM resulted in better crop
discrimination in the first and second dates as compared to
Entropy. The study would be repeated in a different area in
order to convincingly use texture as a feature discriminator in
SAR images.
ACKNOWLEDGEMENTS
This study was possible under the SAR data utilisation
program. For this we are grateful to Director, SAC for his
approval. Our gratitude is also due to Shri J.S. Parihar, Group
Director, Agricultural Resources Group, our mentor, for his
unflinching guidance during the course of the study. We are
also thankful to Shri K. K. Mohanty, for his suggestions and
help during the period.
REFERENCES
Baraldi, A. and Parmiggiani, F. 1995. An investigation of the
textural characteristics associated with the grey level co-
occurrence matrix statistical parameters. /EEE Transactions on
Geoscience and Rem. Sens. 33(2), pp.293-304.
Conners R.W. and Harlow C. A. 1980. A Theoretical
Comparison of Texture Algorithms, /EEE Tr. on Pattern
Analysis and Machine Intelligence, Vol PAMI-2(3).
Fletcher, N.D. 2002. Multi scale texture segmentation of
Synthetic Aperture Radar images. Transfer Report to Ph.D,
University of Bath.
Haralick, R.M. 1979. Statistical and Structural Approaches to
Texture, Proceedings of the IEEE, 67(5), pp. 786-804.
Haralick, R. M., Shanmugam, K. and Dinstein, I. 1973.
Textural features for image classification. /EEE Transactions
on Systems, Man and Cybernetics 3(6), pp. 610-623.
Liew, S.C., Lim, H., Kwoh, K. and Tay, G.K. 1995. Texture
analysis of SAR images. /nt. Geoscience and Rem. Sens.
Symp.(IGARSS). Vol.2 pp. 1412-1414.
Shanmugam, K., Narayanan, V., Frost, V.S., Stiles, J.A. and
Holtzman, J.C. 1981. Textural features for radar image
analysis. [EEE Transactions on Geoscience and Rem. Sens.
19(3), pp. 153-156.
Sklansky, J., 1978. Image segmentation and feature extraction.
IEEE Transactions on Systems, Man and Cybernetics, 8(4), pp.
237-247.
IAPRS & SIS, Vol.34, Part 7, "Resource and Environmental Monitoring", Hyderabad, India,2002
Soh, L.K. and Tsatsoulis, C. 1999. Texture analysis of SAR sea
ice imagery using gray level co-occurrence matrices. /EEE
Transactions on Geoscience and Rem. Sens. 37(2), pp.780-795.
Ulaby, F.T., Kouyate, F., Brisco, B. and Williams, T.H.L.
1986. Textural information in SAR images. /EEE Transactions
on Geoscience and Rem. Sens. 24(2), pp.235-245.