A Study of Feature Extraction Using Divergence Analysis of Texture Features
作者： W. A. Hallada , S. Cox , R. K. Boyd , B. G. Bly
DOI:
关键词:
摘要: An empirical study of texture analysis for feature extraction and classification high spatial resolution remotely sensed imagery (10 meters) is presented in terms specific land cover types. The principal method examined the use gray tone dependence (SGTD). SGTD reduces levels within a moving window into two-dimensional matrix which can be interpreted as probability pairs. Haralick et al (1973) used number information theory measures to extract features from these matrices, including angular second moment (inertia), correlation, entropy, homogeneity, energy. derivation function of: (1) tones an image; (2) angle along frequency calculated; (3) size window; (4) distance between first three parameters were varied tested on 10 meter panchromatic image Maryville, Tennessee using five measures. A transformed divergence measure was determine statistical separability four categories forest, new residential, old industrial each variation parameters.
jaxa.jp参考文章(12)
B. L. Markham, J. R. G. Townshend, Land cover classification accuracy as a function of sensor spatial resolution ,(1981)
A. L. Vickers, J. W. Modestino, A Maximum Likelihood Approach to Texture Classification IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. PAMI-4, pp. 61- 68 ,(1982) , 10.1109/TPAMI.1982.4767197
Robert M Haralick, K.Sam Shanmugam, Combined spectral and spatial processing of ERTS imagery data Remote Sensing of Environment. ,vol. 3, pp. 3- 13 ,(1974) , 10.1016/0034-4257(74)90033-9
Aram M. Mika, Design Trade-Offs For A Multispectral Linear Array (MLA) Instrument Advanced Multispectral Remote Sensing Technology and Applications. ,vol. 0345, pp. 23- 31 ,(1982) , 10.1117/12.933765
R. WELCH, Spatial resolution requirements for urban studies International Journal of Remote Sensing. ,vol. 3, pp. 139- 146 ,(1982) , 10.1080/01431168208948387
Stephen W Wharton, A contextual classification method for recognizing land use patterns in high resolution remotely sensed data Pattern Recognition. ,vol. 15, pp. 317- 324 ,(1982) , 10.1016/0031-3203(82)90034-6
Robert M. Haralick, K. Shanmugam, Its'Hak Dinstein, Textural Features for Image Classification IEEE Transactions on Systems, Man, and Cybernetics. ,vol. SMC-3, pp. 610- 621 ,(1973) , 10.1109/TSMC.1973.4309314
R.M. Haralick, Statistical and structural approaches to texture Proceedings of the IEEE. ,vol. 67, pp. 786- 804 ,(1979) , 10.1109/PROC.1979.11328
Joan S. Weszka, Charles R. Dyer, Azriel Rosenfeld, A Comparative Study of Texture Measures for Terrain Classification IEEE Transactions on Systems, Man, and Cybernetics. ,vol. SMC-6, pp. 269- 285 ,(1976) , 10.1109/TSMC.1976.5408777
Richard W. Conners, Charles A. Harlow, A Theoretical Comparison of Texture Algorithms IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 2, pp. 204- 222 ,(1980) , 10.1109/TPAMI.1980.4767008