5. SUMMARY
In this paper, texture features description of multispectral
imagery and SAR imagery are conducted with Gabor wavelet.
Then we established the texture mapping between two
registered images based on GMM and solved the parameters
with EM algorithm. It can be seen from the results that the
output of transformation has a high similarıty and expression
with the SAR imagery texture. What’s more, the bigger the
number of single Gaussians in one GMM is, the lower
transformed error precision will be. But in fact, the amount of
calculation will increase greatly since the number of single
Gaussians in one GMM increasing. Hence, the value of m
should be selected carefully in the experiment.
Finally, the approach proposed in this paper of texture features
transformed under different imaging conditions has been proved
to be effective.
ACKNOWLEDGEMENTS
This research is supported by National Key Basic Research
Program of China (973 Program, Grant No. 2012CB719903).
At the same time, the project is supported by the National
Natural Science Foundation of China (Grant No. 41171327).
References
Arivazhagan, S., Ganesan, L., Priyal, S. P., 2006. Texture
classification using Gabor wavelets based rotation invariant
features. Pattern Recognition Letters, 27 (16), pp. 1976-1982.
Bovik, A., Clark, M., Geisler, W. S., 1990. Multichannel texture
analysis using localized spatial filter. /EEE Transactions on
Pattern Analysis and Machine Intelligence, 12(1), pp. 55-73.
Clausi, D. A., Jernigan, M. E., 2000. Designing Gabor flters for
optimal texture separability. Pattern Recgnition, 33(11), pp.
1835-1849.
Chellappa, R., Chatterjee, S., 1985.Classification of texture
using Gaussian Markov random fields. /EEE Transaction on
Acoustics, Speech, and Signal Processing,33(4), pp. 959-963.
Chitre, Y., Dhawan, A. P., 1999.M-band wavelet discrimination
of natural textures. Pattern Recgnition, 32(5), pp. 773-789.
Chen, Y., Wang, R., 2007. A method for texture classification
by intergrating Gabor filters and ICA. Acta Electronica
Sinica, 35(2), pp. 299-303.
Dunn, D., Higgins W. E. Wakeley, J. 1994. Texture
segmentation using 2-D Gabor elementary function. /EEE
Transactions on Pattern Analysis and Machine Intelligence,
16(2), pp. 130-149.
Duskunovic, L, Heene, G, Philips, W., Bruyland, L, 2000.
Urban area detection in SAR imagery using a new speckle
reduction technique and Markov random field texture
classification. /nternational Geoscience and Remote Sensing
Symposium. Honolulu, USA, July 24-28.
Haralick, R. M., Shanmugam, K., Dinstein, L, 1973. Textural
features for image classification. [EEE Transactions on
Systems, Man, and Cybernetics, 3 (6), pp. 610-621
Hu, S, Guo D, Sheng, Y, 2001. Extracting textural
information of satelite SAR image based on wavelet
decomposition. Journal of Remote Sensing, 5(6), pp. 424-427.
Ivanov, V. K., Paschenko, R. E., Stadnyk, O. M., etc, 2006.
Radar remote sensing images segmentation using fractal
dimension field. Radar Conference, pp. 217-220.
Kain, A., Macon, M., 1998. Spectral voice conversion for text-
to-speech synthesis. Proc ICASSP. Seattle, USA, May 12-15.
Lopez-Espinoza, E. D., Altamirano-Robles, L., 2008. A method
based on Tree-Structured Markov random field and a texture
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XXXIX-B7, 2012
XXII ISPRS Congress, 25 August — 01 September 2012, Melbourne, Australia
energy function for classification of remote sensing
images.Electrical Engineering, Computing Science and
Automatic Control, CEE 2008, 5" , Mexico city, November
12-14.
Lin, W., et al., 2007. A method of camouflage evaluation based
on texture analysis model of Gabor wavelet. Acta
Armamentarii, 28(10), pp. 1191-1194.
Lin, W., et al., 2009. Detection probability evaluation model
based on texture feature of thermal infrared. Infrared and
Laster Engineering, 38(1), pp. 155-159.
Li, Y., Meng, X., 2008. Image texture feature detection based
on Gabor filter. Journal of Changchun University of
Technology (Natural Science Edition), 29(1), pp. 78-81.
Mallat, S. G, 1989. A theory for multiresolution signal
decomposition: the wavelet reprentation. /EEE Transactions
on Pattern Analysis and Machine Intelligence, 11(7), pp.
674-693.
Ni, L., Zhang, J., Yao, W., 2004. SAR image’s texture analysis
based on wavelet. Geomatics and Information Science of
Wuhan University, 29(4), pp. 367-370.
Pentland, A. P., 1984. Fractal-based description of natural scenes.
IEEE Transactions on Pattern Analysis and Machine
Intelligence, 6(6), pp. 661-674.
Permuter, H., Francos, J., Jermyn, I., 2006. A study of Gaussian
mixture models of color and texture features for image
classification and segmentation. Pattern Recgnition,39(4), pp.
695-706.
Soh, L., Tsatsoulis, C., 1999 Texture analysis of SAR sea ice
imagery using gray level Co-occurrence matrices. IEEE
Transactions on Geoscience and Remote Sensing, 37(2), pp.
780-795.
Shu, N., 1998.Remote sensing image texture analysis and
fractal assessment. Journal of Wuhan technical university of
surveying and mapping, 23(4), pp. 370-373.
Song, Y., Wan, Y., Chen, P., 2006. Textural features analysis
based on GLCM in TM thermal infrared remotely sensed
images . Remote Sensing Information, 4, pp. 24-26.
Song, Y., Liu, B., Xie, J., 2010. Medical image texture features
classification based on Gabor wavelet transform. Computer
Engineering, 36(11), pp. 200-202.
Tuceryan, M., Jain, A. K., 1993. Texture Analysis, Handbook
Pattern Recognition and Computer Vision. World Scientific,
Singapore, pp. 235-276.
Wu, G, Zhang, Y., Lin, X., 2001. Optimal Gabor filter design
for Bi-textured image segmentation. Acta Electronica Sinica,
29(1), pp. 48-50.
Weszka, J. S., Dyer, C. R., Rosenfeld, A., 1976. A comparative
study of texture measures for terrain classification. /EEE
Transaction on Systems, Man, and Cybemetics, 6(4), pp. 269-
285.