Effect of texture measures to separability of land cover classes using ERS SAR images

Texture features based on Haralick's co-occurrence matrix were compared for land cover and forestry classification purposes. According to these results, the best texture features were Angular Second Moment, Mean and Entropy, the worst Correlation and Standard Deviation. The best SAR-images were taken during wet snow or ground. Usually, the larger the window used to construct the co-occurrence matrix, the better the results. The suitable length of the spatial step depended on texture feature and classes. The directionless texture features performed usually well. The results of the performed classification experiment were disappointing.

[1]  Josef Kittler,et al.  Pattern recognition : a statistical approach , 1982 .

[2]  V. Rich Personal communication , 1989, Nature.

[3]  T. M. Lillesand,et al.  Remote sensing and image interpretation. Second edition , 1987 .

[4]  H. Kramer Observation of the Earth and Its Environment , 1994 .

[5]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[6]  T. Strozzi,et al.  SAR interferometric and differential interferometric processing chain , 1998, IGARSS '98. Sensing and Managing the Environment. 1998 IEEE International Geoscience and Remote Sensing. Symposium Proceedings. (Cat. No.98CH36174).

[7]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .