Confidence score
A confidence score indicates how confident a model is that a detected object is accurately identified.
A confidence score is a percentage value between 0 and 1. A score that is close to 1 indicates that the model is confident that the object is accurately identified. A score that is close to 0 indicates that the model is not confident that the object is accurately identified. For example, a confidence score of 0.75 indicates that the model has a confidence of 75% that the object is identified correctly.
Inspecting mode
When an inspection is run in Inspecting mode, a confidence score is generated.
When you are configuring an inspection in Inspecting mode, you can add a high value in the Minimum confidence score field. The high confidence score filters detected objects with low confidence scores from being inspected.
For example, enter a minimum score of 0.9 so that only objects that are detected with at least 90% confidence are inspected.