A Method for Medical Microscopic Images’ Sharpness Evaluation Based on NSST and Variance by Combining Time and Frequency Domains

. 2022 Oct 7;22(19):7607. doi: 10.3390/s22197607

Algorithm 1. Pseudo-Code of the Algorithm

Input: N₁ is the number of pictures to be processed.
Output: H is the definition of the evaluation value.

1:
$L \leftarrow 1$
2:
$N \leftarrow 3$ Decomposition series
3:
for $L$ to $N_{1}$ by 1 do
4:
$i m \leftarrow i m r e a d (‘ i m a g e p a t h ’)$
5:
$i m \leftarrow r g b 2 g r a y (i m)$
6:
$i m \leftarrow i m 2 d o u b l e (i m)$
7:
The image is decomposed by $N S S T$ to obtain low-frequency component $f_{1}$ and high-frequency components $f_{2 k}, f_{3 k}, and f_{4 k}$ .
8:
$[V_{1}, V_{2}, V_{3}, V_{4}] \leftarrow g e t_v a r i a n c e (i m, f_{1}, f_{2 k}, f_{3 k}, f_{4 k})$
9:
The energy coefficients of each high-frequency sub-band are processed and added to obtain $E_{1}, E_{2}, and E_{3}$ . The low-frequency coefficient is $E_{L}$ .
10:
$E_{H} \leftarrow s * E_{2} + (1 - s) * (E_{3} + E_{4}) / N$
11:
$H \leftarrow E_{H} / E_{L}$
12:
end for