The performances of two versions of the proposed morphological multi-scale metric, the Morphological Pyramid Peak Signal-to-Noise Ratio measure, MP-PSNR, and the Morphological Wavelet Peak Signal-to-Noise Ratio measure, MW-PSNR, are presented and discussed.
Previous work on the quality assessment of the DIBR-synthesized views and multi-scale image quality assessment is also shortly reviewed in Section 2. In Section 3, we describe two versions of the proposed multi-scale metric, based on two types of multi-resolution decomposition schemes, morphological pyramid, and morphological wavelets.
Finally, multi-scale metric Morphological Wavelet Peak Signal-to-Noise Ratio, MW-PSNR, is calculated as: mathit{mathsf{M}}mathit{mathsf{W}}_mathit{mathsf{PSNR}}=mathsf{10}cdot { log}_{mathsf{10}}left(frac{{mathit{mathsf{R}}}^{mathsf{2}}}{mathit{mathsf{M}}mathit{mathsf{W}}_mathit{mathsf{M}}mathit{mathsf{S}}mathit{mathsf{E}}}right) (12).
We have explored two versions of morphological multi-scale metric, Morphological Pyramid Peak Signal-to-Noise Ratio measure, MP-PSNR, based on morphological pyramid decomposition and Morphological Wavelet Peak Signal-to-Noise Ratio measure, MW-PSNR, based on morphological wavelet decomposition.
These eigenvectors represent a multi-scale metric for grouping sites, and thus do not represent any computed soil parameter that was measured at sampling sites.
For example, one scaling metric can be (3).
Instead, we left the scaling metric (Nsim (0,1)) unchanged.
Most of the current multi-scale IQA metrics use linear filters in the multi-resolution decomposition.
A multi-scale supervised neural architecture, called Multi-Scale SOON, is proposed for natural texture classification.
Firstly, NSCT is employed to decompose the image into multi-scales.
It is a multi-stakeholder, multi-variable, multi-scale problem.
