Photo Photo Photo Photo Photo Photo

Print
E-mail
Remote Sensing: NEW SUPERVISED SAR IMAGE CLASSIFICATION TECHNIQUE BASED ON WAVELET-TRANSFORMATION METHOD

 

NEW SUPERVISED SAR IMAGE CLASSIFICATION TECHNIQUE


BASED ON WAVELET-TRANSFORMATION

METHOD

S. M. Ali

Remote Sensing Unit- College of Science- University of Baghdad IRAQ- Baghdad- Al-Jaderyia

ABSTRACT

A new supervised classification technique will be introduced based on stationary wavelet-transform. The presented technique is used to classify coherent images as well as SAR images. The SAR image is highly corrupted by signal-dependent, multiplicative, noise. Therefore, SAR image by our classification technique decomposed into 4 sub-bands using two-level stationary wavelet-transform. For each image point, a 4-dimensional vector is constructed whose components represent the same location values at the 4-wavelet subbands. A minimum distance measure criterion is used to classify the processed image regions. The introduced classification algorithm can be categorized as supervised classification technique.

Keywords, Classification Method, Supervised Classification Method, Wavelet Classification Method.



alt

 

S5 Box

Login



Register

*
*
*
*
*

Fields marked with an asterisk (*) are required.