Anomaly Segmentation

This article describes the process for detecting anomalies by using non-anomalous good image samples. In this process, the model is trained using good images, eliminating the need to collect and label rare defect data before training. The output inc...

When creating a new anomaly model, you can clone from an existing model to populate the same set of good images and test images in the new model. You can edit the images, remove or add images, and specify the region of interest. In the Anomaly M...

Once an anomaly model result is available based on the good images and test images, you can view the results under the Results tab of the project catalog. The Results tab displays the anomalies indicated with red dots on the top right of the te...

Once you have created an anomaly model, the results of anomaly model consisting of anomaly category label, other attributes like pixel anomaly percent etc. can be exported to catalog for use in other visualization jobs. You can also access the resul...