ZEISS Knowledge Base
Help
ZEISS Knowledge Base
Search

Intellesis Object Classification

This module offers the functionality to classify objects based on measured parameters of an analyzed image using machine-learning algorithms and to create and to train such a model for object classification. Since the input for the object classification is an analyzed image containing a result table, the functionality of the Image Analysis module is also required for the complete workflow.

Workflow Overview for Intellesis Object Classification

The workflow to train and use an Intellesis object classification model consists of three main steps:

Training User Interface Intellesis Object Classification

1

Classification Settings
Here you can set the classes for labeling/classifying the objects, see Classification Settings.

2

Image Import Section
Here you can import and select the images you want to use for classification, see Image Import Section Intellesis Object Classification.

3

Image View
Here you have your analyzed image and can label the objects by clicking on them.

4

Table
This table displays your analysis results and can be used for labeling the objects in your image, see Object Classification Table.

5

View Options
Here you have some general view options on the Dimensions and Display tab, as well as specific labeling options on the Labeling Options tab, see 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.

Labeling Options Tab

Parameter

Description

Mode

–


Selection

Activates the selection mode to select objects in the image without labeling them.

–


Labeling

Activates the labeling mode to label the objects in your image.

–


Erase

Activates the erasing mode to delete 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 table displays the values for Measurement Features selected inside the image analysis, but not the ones that are used internally to classify the objects.

Image Import Section Intellesis Object Classification

Here you can load and select the images you want to use for training. When you click on a loaded image, the image will be visible in the Image Area. Only images containing image analysis results can be opened to train an object classifier.

Parameter

Description

Import from Archive

Opens a dialog to browse the archive to select the image for import. The image is copied to the location defined under Maintenance > General Options > Intellesis.

Import Images

Opens a file browser to select the image for import.

Image list

Displays the list of imported images. If you load a new image only the preview image, file name and type of image are displayed. As soon as you have started to label an image of a larger data set, a list of the images that contain labels is displayed, containing dimension and image number (e.g. for a z-stack, Z:400 indicates that the slice number 400 contains labels).

If you click on this information, the corresponding image 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 you have already labeled.

Creating and Training an Intellesis Object Classification Model

  1. You have licensed the AI Toolkit and activated it under Maintenance > Toolkit Manager.
  2. You are in Manage Templates.
  3. You have a CZI image with image analysis results. For detailed information on analysis, see Image Analysis.
  1. For Show, select Intellesis Object Classification Models.
  2. In the top right tool bar, click .
  3. The user interface for training opens, see Training User Interface Intellesis Object Classification.
  4. In the top left corner, click Import Images. To open an image from the archive, click Import from Archive.
  5. A file browser or the archive browser opens.
  6. Select the image for training from the file system and click Open. When loading the image from the archive, select the image and click OK.
  7. If the image analysis contains more than one class and channel, the Select Region Class and Channel(s) dialog opens.
  8. Select the region class and the channels you want to use for classification and click OK.
  9. The image is displayed in the list. Note that all imported images are included in your model.
  10. If you have imported an image from the archive, it is copied to the location defined under Maintenance > General Options > Intellesis.
  11. Select the image from the list.
  12. The image is displayed, and the table shows the data of the analysis result.
  13. On the left side, add as many classes as you need for your object classification by clicking Add Class.
  14. You have created the classes that you want to distinguish.
  15. To change the label color for a class, click on the color field of the list entry and select one from the window.
  16. To rename a class, right click on the entry, select Rename, enter a new name and click . Alternatively, double click the name entry, enter a new one and click , or press Enter.
  17. In the Labeling Options tab, click .
  18. You are now in labeling mode.
  19. In the classes list, select a class and click on an object that belongs to this class in the image or in the table.
  20. You have labeled the object and assigned it a class.
  21. Repeat the labeling for the objects of the different classes you created.
  22. Click Train & Classify.
  23. Your model is trained based on the labeling and a prediction is displayed.
  24. If you are not satisfied with the result, you can label more objects, click Train & Classify again, and iteratively improve your results.
  25. When you are satisfied with the result, click Finish.
  26. All changes are saved, and the training interface is closed.
  1. You have successfully created and trained a model for object classification. You can now use it to classify objects in your analyzed images with the Intellesis Object Classification tool, see Using an Intellesis Object Classification Model for Image Processing.

Importing an Intellesis Object Classification Model

  1. You have a trained model available for import.
  1. Under Manage Templates > Show, select Intellesis Object Classification Models.
  2. In the top right tool bar, click .
  3. A file browser opens.
  4. In the file browser, select the model file from the file system, and click Import.
  1. You have imported a model, and it is available in the list of object classification models. You can now use it to classify objects in your images or open it (e.g. for training) by double clicking on it.

Exporting an Intellesis Object Classification Model

NOTICE

notice

Risk of non-functioning models in new ZEN core versions

In case of changes in Python libraries, trained models can stop working on a new version of ZEN core and need to be retrained first. Retraining is only possible if the model contains the images, or the images are generally still available. To be able to retrain your model, consider the following solutions:

  1. Export your model with your images, see Exporting an Intellesis Object Classification Model with Images.
  2. Make a backup of the images used for training the model, e.g. on your (external) hard drive.
  1. You are in Manage Templates.
  2. You have created an object classification model, see Creating and Training an Intellesis Object Classification Model.
  1. For Show, select Intellesis Object Classification Models.
  2. Right-click the model you want to export and select Export.
  3. A file browser opens.
  4. Select the file location and click OK.
  1. The model is exported to that location. It contains the trained classification routine. Such a model is meant to be used only for classifying objects in an analyzed image, but not for the training process anymore.

Exporting an Intellesis Object Classification Model with Images

  1. You are in Manage Templates.
  2. You have created an object classification model, see Creating and Training an Intellesis Object Classification Model.
  1. For Show, select Intellesis Object Classification Models.
  2. Right-click the model you want to export and select Export (with Images).
  3. A file browser opens.
  4. Select the file location and click OK.
  1. The model is exported to that location. It contains the trained object classification routine and the images used for the training. Such a model can be used for classifying objects in an analyzed image and can be retrained in the future.

Intellesis Object Classification Workbench

This workbench enables you to perform an object classification on your analyzed image(s), see Using an Intellesis Object Classification Model for Image Processing.

Create Result Table Tool

This tool creates a standalone table with the measurement results embedded in an image.

Parameter

Description

All Slices

Activated: Creates the table for all image slices.
Deactivated: Creates the table only for the current slice.

Region Class

Selects the region class for which the table is created (e.g. for the detected Object, or the Background).

ON THIS PAGE

PRODUCTS
ZENX Ray SoftwareEM SoftwareSolutions Lab
ABOUT ZEISS
AboutCareerNewsroomCompliance
Social Media
LinkedInFacebookYouTubeXFlickrInstagram
Impressum
Carl-Zeiss-Strasse 22
73447 Oberkochen
Germany
Legal