Title :
Gabor vs. GMRF features for SAR imagery classification
Author :
Torres-Torriti, Miguel ; Jouan, Alexandre
Author_Institution :
Dept. of Electr. & Comput. Eng., McGill Univ., Montreal, Que., Canada
fDate :
6/23/1905 12:00:00 AM
Abstract :
A comparison of the ability to discriminate among distinct regions in synthetic aperture radar (SAR) imagery using textural features based on two different methods is presented. Features are generated from Gauss Markov random field (GMRF) model parameters and from Gabor convolution energies. The discrimination ability is evaluated in terms of misclassification errors resulting from tests performed on a patchwork of different MSTAR clutter regions
Keywords :
Gaussian processes; Markov processes; convolution; feature extraction; image classification; image texture; radar clutter; radar imaging; random processes; remote sensing by radar; synthetic aperture radar; GMRF features; GMRF model parameters; Gabor convolution energies; Gabor features; Gauss Markov random field; MSTAR clutter regions; SAR imagery classification; misclassification errors; remotely sensed imagery; synthetic aperture radar imagery; textural features; Convolution; Detectors; Gabor filters; Gaussian processes; Image edge detection; Image segmentation; Markov random fields; Performance evaluation; Synthetic aperture radar; Testing;
Conference_Titel :
Image Processing, 2001. Proceedings. 2001 International Conference on
Conference_Location :
Thessaloniki
Print_ISBN :
0-7803-6725-1
DOI :
10.1109/ICIP.2001.958305
