Title :
On the use of transform features for SAR image classification
Author :
Manian, Vidya ; Vasquez, R.
Author_Institution :
Dept. of Electr. & Comput. Eng., Puerto Rico Univ., Mayaguez, Puerto Rico
Abstract :
Transform features are used for classification of regions in SAR images. The three sets of features are based on Fourier transform, wavelet transform and logical transform. Experiments are conducted and the performance of the features are compared. The best results are obtained with wavelet and logical transform features
Keywords :
Fourier transforms; geophysical signal processing; geophysical techniques; image classification; radar imaging; remote sensing by radar; synthetic aperture radar; transforms; wavelet transforms; Fourier transform; SAR; geophysical measurement technique; image classification; image region analysis; land surface; logical transform; radar imaging; radar remote sensing; synthetic aperture radar; terrain mapping; transform feature; wavelet transform; Error correction; Error correction codes; Feature extraction; Fourier transforms; Frequency; Geometry; Image classification; Image segmentation; Sampling methods; Wavelet transforms;
Conference_Titel :
Geoscience and Remote Sensing Symposium Proceedings, 1998. IGARSS '98. 1998 IEEE International
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-4403-0
DOI :
10.1109/IGARSS.1998.699675
