Statistical features can provide valuable information alongside a CCI-Feature or a Case-Feature. Use this feature to get statistical properties of spectra resolved by pixels in the scene.
Statistically derived properties of spectra are obtained. The resulting image describes statistical values by their gray values.
Statistical features are typically used as additional information together with a Case- and/or CCI-Feature. For example; the discrimination of background and foreground often can be done very robustly by means of the mean intensity feature. By streaming such a statistical information parallel to a CCI-Feature (classification IDs), the client machine vision application might be able to distinguish foreground from background objects more robustly.
The data set plastics is loaded (the data set is selected in the project browser to the left). Per plastic group a spectra set is defined and is shown in the Selected Spectra graph as well as their originating pixel positions by colored markers in the Input view.
The model method Statistical Features is selected in the ribbon menu. The control panel of this method is shown on the lower right. The result of the method is shown in the Output view.
The preprocessing method Intensity is selected in the ribbon menu. The statistical feature Mean is selected. Spectra are shown in the range ~1000-1700nm.
The pixel values of the output image correspond to the mean of all reflectance spectra in the range from 1000-1700nm. Therefore, the output corresponds to the relative reflectance degree of 3 plastic plates in the NIR-range (1000-1700nm).
On the feft hand side, information on the loaded data set are available like the Statistics panel as well as descriptive parameters attached to the data set.
Method parameters are shown in the panel to the lower left of the perspective.
Statistical feature selector
Select a feature of interest
The output image corresponds to the statistical minimum value of spectra per pixel.
The output image corresponds to the statistical maximum value of spectra per pixel.
The output image corresponds to the statistical mean value of spectra per pixel.
The output image corresponds to the statistical dynamic of spectra per pixel. The dynamic is the difference of maximum and minimum.
- Select one of the statistical methods
- Apply preprocessing
- Study the gained output image
- Save the model for later usage (e.g. to set up the live streaming)
Found 3 search result(s) for "statistical feature".
... 3 (RGB). depends on the model, which was used to create the stream. e.g. a CCI feature will produce a color image stream with spectral size = 3 (RGB), a statistical feature will create a grayscale stream with spectral size = 1 15 uint8 Bytes per ...
Jun 02, 2020
... pixel value. modelDyn1stDerplastics.png The statistical feature methods allows an extraction of information based on statistical methodology. Preprocessing 1st derivative was applied to the data beforehand. The spectral dynamic is extracted ... class ID per taught material (i.e. per spectra set). Model a ...
Jul 07, 2020
... cube is visualized in form of a color or a monochrome image. The image information is obtained by applying feature functions to the hyperspectral cube. cubeprojection.png As default, the preview feature is selected (in the ribbons Feature group) and results in a color image. By selecting a statistical feature like Mean, the mean ...
Jun 16, 2020
© 2019 by Perception Park GmbH
The content of this page and any attached files are confidential and intended solely for the addressee(s). Any publication, transmission or other use of the information by a person or entity other than the intended addressee is prohibited. If you receive this in error please contact Perception Park and delete copied material. Perception Park GmbH,Wartingergasse 42, A-8010 Graz; Austria; FN 400381x