Training User Interface Intellesis Object Classification

1	Classification Settings Here you can set the classes for labeling/ classifying the objects. For more information, see Classification Settings.
2	Image View Here you have your analyzed image and can label the objects by clicking on them.
3	Table This table displays your analysis results and can be used for labeling the objects in your image. For additional information, see Object Classification Table.
4	Image Gallery Here you can import and select the images you want to use for classification. For more information, see Image Gallery (Object Classification).
5	View Options Here you have some general view options of the Dimensions Tab and Display Tab as well as specific labeling options on the Labeling Options Tab.

Classification Settings

Parameter		Description
Model		Displays the model name.
Selected Region Class		Displays the region class selected for classification.
Selected Channels		Displays the channels selected for classification.
Classes list		Displays all the classes for classifying the objects. The color of the class can be changed by clicking on the color field. Renaming of a class is possible by right click menu.
Add Class		Adds a new class to the Classes list.
Delete Class		Deletes the currently selected class from the list.
Train & Classify		Starts the training for the object classification setting.
Display
–	Label	Displays the labels in the image.
–	Prediction	Only available after a training has been performed. Displays the predictions in the image.
Finish		Saves the classification setting and closes the setup.
Cancel		Closes the setup without saving the changes.

Image Gallery (Object Classification)

On the right under Images & Documents, you find the area for handling the images. Here you can load and select the images you want to use for classification. When you click on a loaded image, the image is displayed in the Center Screen Area.

In the list of images you have certain possibilities to gain advanced information about the image. If you load a new image, only the preview image, file name and type of image are displayed. When you have labeled certain slices (for example), they are listed under the image entry. If you click on this information the corresponding image (slice) is automatically displayed in the center screen area. This is very helpful when you are working with large data sets such as z-stacks, scenes or time-series and you want to quickly load the image which you have already labeled.

Parameter	Description
Import Images	Opens the file browser to select the images for import.

Labeling Options Tab

Parameter		Description
Mode
–	Selection	Activates the selection mode. You can select objects in the image without labeling them.
–	Labeling	Activates the labeling mode. You can label the objects in your image.
–	Erase	Activates the erasing mode. You can erase the labels in your image.
Object Display		Sets how the label are displayed in the image.
–	Fill	Displays the label as filled objects.
–	Outline	Displays the label as an outline.
Opacity		Sets the opacity of the label in the image.

Object Classification Table

Here the analyzed objects of the image are displayed. You can also use the table to label the objects, see Creating and Training an Intellesis Object Classification Model. This table is linked to the image, which means selecting a row in the table centers the view on the respective object in the image and vice versa. If the image is not zoomed to extent, a click on an object in the table centers this object in the image view and adapts the zoom level if necessary (by zooming out). The table can be sorted by each column by simply clicking on the header.

The table only displays the measurements features selected inside the image analysis, not the ones that are used internally to classify the objects.

Parameter	Description
ID	Displays the unique ID of the objects in the analyzed image.
Label	Displays the label class attributed to the respective object.
Prediction	Displays the predicted label using all labels from all available images.
Confidence	The confidence value in % for the predicted label of every individual object.
Measurement features	Additionally to ID and Label, the values of the various Measurement Features are displayed in the table.