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


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). If ‘Classify’ is enabled, you can assign a class to each annotated defect. Then you can start the training - further information about the training options can be found in the section training.

Local image


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


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 see the Classifier. This can also be achieved by combining Detector and Classifier as separate modules as described in this video. However, classifying objects directly in the Detector is easier and faster.


Each detected object is surrounded by a rectangle with percentage showing confidence of detection. Confidence threshold can be changed in order to keep only the objects, which were detected with confidence equal or higher than the threshold.

Detected objects are added into the ‘detectedRectangles’ array. Each object has its size, coordinates and id.


 "detectedRectangles": []


 "detectedRectangles": [
      "height": 87,
      "y": 45,
      "width": 52,
      "id": 15468795458,
      "x": 822,
      "classNames": [
          "id": 1527681328266,
          "label": "Defect"

results matching ""

    No results matching ""