Aivia Software

Classifier view

The Classifier View is a special display option in Aivia that allows you to create and apply custom object classifications on analyzed data. The classifier uses a random forest algorithm to identify unique features (i.e. measurements) for classification.

The Classifier View is accessed by clicking on the Classifier View icon  on the zoombar.

On this page:


The Classifier View button  is located on the zoombar directly above the Image Panel. When the Classifier View is launched, the Display Settings and (Pre-version 12) Analysis Panel will collapse to the right side of the Aivia window. You can click on the vertical separator on the right side of the Aivia window to expand the right panel.

The Classifier View has two sections: the image viewer on the left and the gallery on the right. Controls for the tool are found in the gallery section.

Classifier View interface


The Classifier View toolbar is located at the top of the gallery on the right side of the Classifier View. The toolbar allows you to perform file actions related to the Classifier, such as selection, creation, and saving.

The function for each item in the toolbar is summarized in the table below:


The dropdown menu lets you select a loaded classifier to apply to your data.
Create New Classifier
This option allows you to create a new, blank pixel classifier for teaching.

This option removes the selected classifier from Aivia. This will not delete the selected classifier from its file.

This option allows the user to load a pre-trained classifier (.classifier) from a file into Aivia.

This option allows the user to save the current classifier to a file.
Export Classifier Data to CSV

This option allows the user to export the classifier data (trained objects and measurements) to an Excel-readable comma-separated value (CSV) file.
Reload Classifier

This option reloads the current classifier to its previously saved state, discarding any changes made to the classifier.
Select Measurements

This option launches a window that lets you specify the measurements to use in the classifier.
Toggle Multi-Selection

This option turns on the multi-selection cursor, allowing you to select multiple objects by clicking on each object in the gallery separately without holding down the Shift or Ctrl key on your keyboard.

The gallery shows a thumbnail of all objects on the image as well as the thumbnails of any objects that are taught during the current session. The gallery separates the thumbnails by classes indicated by a colored header. You can expand/collapse each class separately.

In the collapsed view, a generic icon (on the right) indicates the number of additional thumbnails/objects that are in the class. Clicking on the generic icon will fully expand the current class and collapse all others.

Classifier bar

The Classifier bar is located at the bottom of the gallery and provides a number of actions for teaching and applying the classifier on the image.

General usage

Apply a classifier

To apply a classifier, select the classifier to run from the Classifier dropdown menu and click the Apply button in the lower-right corner of the gallery. If the data has existing classifications, applying a classifier will remove the existing classifications and create new ones.

On apply, the classifier will look at each object and assign a class. If you have Color by Class turned on in the Object Set Settings, the colors of the objects will change in accordance with their assigned categories.

You can also view the objects by class in the Spreadsheet panel as subsets.

Create a new classifier

You will need to have analysis results, such as outlines and surfaces, to use Classifier View. You can generate results using one of the recipes or through manual editing. Tracks are currently not supported.

You can create a new classifier from scratch by clicking on the Create New Classifier  button in the Classifier View toolbar. You will be prompted to enter a name and specify the object type (see right). The general workflow for creating a classifier from scratch is as follows:

  1. Select the object type you wish to analyze using the Classifier View.

  2. Create classes of objects as needed for identifying each phenotype.
  3. Teach the classifier by selecting a few representative objects from each category and adding them to the relevant class gallery; click Teach when you have provided examples from each class.
  4. Update the classifier as needed by adding additional object examples.
  5. Select measurements to use or exclude from the classifier.
  6. Apply the classifier to the image.

More information on how to use the Classifier View can be found in the How to classify objects page.