Detector

Detector module allows you to find and possibly classify an object in the image.

Training

Annotations

First annotate defects in the image - size of the annotation should be just enough to fit the whole defect without too much excess background (especially when the background is very variable).

To delete an annotation, you can either use the trashcan icon in the top right corner or press 'Delete' when the annotation is selected. If ‘Classify’ is enabled, you can assign a class to each annotated defect - Then you can start the training.

Auto-annotations

To speed up the annotation process, there is a possibility to train a model on a small amount of annotations first and then use the predictions of this model to quickly make more annotations for further training.

If we select a trained model from list of models and then go to training tab, we can see predictions of that selected model on our images. They are marked with red rectangles with percentages.

Clicking Set annotations will automatically set annotations for all the detected rectangles in selected image.

It is possible to edit these annotations afterwards if we want to make them more precise. We can also add more annotations, delete them if some of them are wrong or change their classes if Classify is enabled, same as with normal annotations.

After auto-annotating enough images, we can start another training, which should offer better results than the one we made with just a few annotations before.

Rotate

This allows you to search for objects rotated in various directions.

Classify

This adds the option to classify the object into one of the classes. If the classification is enabled, each marked object needs a class to be assigned to it.

For more details visit Classifier. This can also be achieved by combining Detector and Classifier as separate modules as described in the video below. However, classifying objects directly in the Detector is easier and faster.