Index

Before starting learning task it is highly recommended to read Recognition and Constraints sections from introduction.

Next, when one or more object models are learnt you may proceed to object recognition.

You should click Recognize button in the main window to start object recognition. Select one or few images for object recognition.

When you have at least one object learnt you may use them in object recognition process - to check whether a test image contains the learnt object.

If you have opened few images you can use Play button to go through files automatically.

You must select one or more objects listed in the list box on the right of the SentiSight Demo Recognition Window.

During recognition process algorithm is able to locate objects in the image and display recognition score.

If recognition fails or no object models selected the object in the image is not selected. A Similarity Threshold allows you to manipulate the recognition results. The similarity score is a comparative score which shows how likely the test image contains the object. A high similarity score suggests that test image contains the object. On the other hand, a low similarity score implies that test image displays noise. See Options->Matching Threshold.