You have the option to use TCA in combination with Intellesis Object Classification models. The following job templates are provided:

  • Component Cleanliness Testing with Object Classification
  • Component Cleanliness Testing with Object Classification (Loaded Image)
  • Component Cleanliness Testing with S&F and Object Classification
  • Component Cleanliness Testing with S&F and ML Object Classification and HM

As a Supervisor, you can adapt the provided job templates to your needs. To exchange the model in TCA job templates, select the desired model in the Intellesis Object Classification workbench in the Intellesis Object Classification tool.

In case the particle type differentiation using the conventional segmentation method is not sufficient and metallic particles are in brightfield contrast by default very dark or almost black, use the following Intellesis Object Classification models.

TCA with Intellesis Object Classification improves the automated detection of metallic particles, especially the darker ones.

  • Component Cleanliness Object Classification Model (Pol-90, Pol-0)
  • Component Cleanliness Object Classification Model (Pol-90, Pol-45)
  • Component Cleanliness Object Classification Model (Pol-90, Pol-135)
  • MICA.MnM Object Classification Model (Pol-90, Pol-0)

Mica particles are layered silicates which are used as fire protection element in e-mobility. Mica particles are very shiny and therefore often misclassified as metallic shiny particles. With ZEN core v3.13, the Mica Intellesis Object Classification model is available. The Mica model MICA.MnM Object Classification Model (Pol-90, Pol-0) is well suited to classify mica particles automatically as non-shiny.

NOTICE

notice

Wrong polarization channel combination of model and image

The Pol channel combination of the selected model must be identical to the channel selection in the Tiles Region workbench, which is by default Pol-90 and Pol-135. To decide which channel selection is the best one for your microscope system, see POL Camera Technology.

To tailor the pre-trained TCA Component Cleanliness Object Classification Model model to your needs, see Retraining a Model for TCA.