Major Update: Semi-Automatic Classification Plugin v. 4.7.0

This post is about a major update for the Semi-Automatic Classification Plugin for QGIS, version 4.7.0.

Following the changelog:
-added multiplicative and additive factors in the band set tab, which allow for on the fly conversion to TOA
-improved the threshold settings for spectral signatures, which are now saved in the signature list file
-added options for the extent calculation in Band calc
-added calculation of Kappa hat for accuracy assessment
-added button for clearing Landsat download table
-added button for sorting band set by name
-added button for creating external overviews of bands
-added button for automatic calculation of signature thresholds
-added button for cumulative cut and standard deviation stretch of input image
-added button for showing and hiding input image
-added button for zooming to ROIs and previews
-added slider for transparency of previews
-bug fixing

This version adds several new functions. In the tab Band set, it is possible to set a multiplicative rescaling factor and additive rescaling factor for each band (for instance using the values in Landsat metadata), which allow for on the fly conversion to TOA while calculating spectral signatures or classifying.
Also, a new button allows for sorting automatically bands by name, giving priority to the ending numbers of name.

The statistics in tab Accuracy now include also the Kappa hat for classes and the whole classification, which are useful for accuracy assessment.

The tab Signature threshold now includes a button for the automatic calculation of a threshold for each signature, based on the variance thereof (currently works for Minimum Distance and Spectral Angle Mapping calculating a distance or an angle). Also, thresholds are saved in the signature list file.

The tab Band calc now allows for the definition of raster output extent.

Other improvements to the interface allow for the rapid visualization of images and classification previews. Very soon I am going to publish a tutorial about these new features.
For any comment or question, join the Facebook group and a Google+ Community about the Semi-Automatic Classification Plugin.