Automated texture recognition system based on 2D minimum variance spectral estimation

The primary feature of any image texture is the spatial frequency content. This paper proposed the use of a 2D minimum variance spectral estimation (MVSE) method for recognizing target multispectral image textures. The power spectral density of the target texture is estimated via MVSE. This estimate is then used as a feature to discriminate between target and nontarget textures. A remotely sensed multispectral image of a row crop agricultural field is analyzed and, the corresponding results are presented to illustrate the applicability of the proposed technique.

[1]  Rama Chellappa,et al.  Enhanced segmentation of SAR images using non-Fourier imaging , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[2]  Roger L. King,et al.  Multiresolutional texture analysis of multispectral imagery for automated ground cover classification , 2002, IEEE International Geoscience and Remote Sensing Symposium.

[3]  Steven Kay,et al.  Modern Spectral Estimation: Theory and Application , 1988 .

[4]  Reiner Lenz,et al.  Generalized co-occurrence matrix for multispectral texture analysis , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[5]  Stuart R. DeGraaf,et al.  SAR imaging via modern 2-D spectral estimation methods , 1998, IEEE Trans. Image Process..

[6]  B. Porat,et al.  Digital Spectral Analysis with Applications. , 1988 .