This post is about a new update of the Semi-Automatic Classification Plugin v. 7.8.0.
Following the changelog:
-new tool for analysis of neighbor pixel with convolution matrix
-improved performance with multiprocessing calculations
-fixed conversion to vector
This new version includes a new Preprocessing tool named Neighbor pixels.
This tool allows for the calculation of several neighbor pixel statistics for every band of a band set defined in the Band set.
The statistics are calculated for every pixel of the input raster considering the values of the neighbor pixels. Neighbor pixels are defined through a distance or through a custom matrix.
For example, the following matrix represents the neighbor pixels within a distance of 1 pixel from a central pixel, resulting in a 3x3 matrix.
| Neighbor | Neighbor | Neighbor |
| Neighbor | Center | Neighbor |
| Neighbor | Neighbor | Neighbor |
Several statistics are available. The statistic Sum will result in a raster convolution. For instance, this can be useful to apply an image filter to all the bands a band set for photointerpretation.
An output band is created for every band in the band sets.
Also, the multiprocessing calculations have been optimized and calculations should generally be more rapid compared to previous version.
For any comment or question, join the Facebook group or GitHub discussions about the Semi-Automatic Classification Plugin.