Martin Coath edited section_Methods_For_results_derived__.tex  about 8 years ago

Commit id: a3062bf45520816e500cd4b8a78449f1dcb89dda

deletions | additions      

       

\begin{enumerate}  \item the number of pixels $m$ corresponding to half the required window size $w$ is calculated: $m = \mathrm{floor}(\frac{w}{2})$  \item thus the working window size is $n = 2 \cdot m+1$   \item assemble the vector $\vec{k}_{j}$ of values for a horizontal window of $n$ contiguous pixels $k_{[i,j-; i,j+1; i,j+n-1]}$ $k_{[i,j-m : i,j : i,j+m]}$  \item repeat with $\vec{k}_{i}$, a vector of values for a vertical window of $n$ pixels $k_{[i,j; i+1,j; i+n-1,j]}$ $k_{[i-m,j : i,j : i+m,j]}$  \item both vectors are normalized, so they can be treated as distributions, and the Skewness $\gamma$ of each distribution, \textit{i.e.} the asymmetry in the gray-scale values in both direction, is calculated, $\gamma_j$ and $\gamma_i$  \item the \textsc{skv} value of the pixel is the larger of the two values $\max(\gamma_j, \gamma_i)$  \end{enumerate}