Systholic Boolean Orthonormalizer Network in Wavelet Domain for SAR Image Despeckling
This addresses speckle removal in SAR images for remote sensing applications, but appears incremental as it builds on wavelet transforms and orthonormalization techniques.
The paper tackles the problem of removing speckle with unknown variance from SAR images by proposing a novel method that applies a Systholic Boolean Orthonormalizer Network in the wavelet domain, resulting in despeckling performance that compares favorably to most existing methods.
We describe a novel method for removing speckle (in wavelet domain) of unknown variance from SAR images. The me-thod is based on the following procedure: We apply 1) Bidimentional Discrete Wavelet Transform (DWT-2D) to the speckled image, 2) scaling and rounding to the coefficients of the highest subbands (to obtain integer and positive coefficients), 3) bit-slicing to the new highest subbands (to obtain bit-planes), 4) then we apply the Systholic Boolean Orthonormalizer Network (SBON) to the input bit-plane set and we obtain two orthonormal output bit-plane sets (in a Boolean sense), we project a set on the other one, by means of an AND operation, and then, 5) we apply re-assembling, and, 6) re-sca-ling. Finally, 7) we apply Inverse DWT-2D and reconstruct a SAR image from the modified wavelet coefficients. Despeckling results compare favorably to the most of methods in use at the moment.