Good practices for collecting images

Collect images on the same device as you will use in the final application.

• Option 1: Collecting on-site directly

  • Make sure to have good variance, collect the data at different times of the day, at different lighting conditions (if there is no industrial lighting) and so on.
  • Make sure there is no systematical error (for example only collecting data after a specific shipment has come in etc).

• Option 2: Collecting simulated data for a prestudy

  • Make sure to have good variance, same as above.
  • Don't use the same objects in multiple images. If you have to, because you only have a small amount of samples, make sure to set a few objects aside and mark them as "only test" objects. Otherwise the evaluation will not be meaningful! You can mark images for testing by creating a dedicated Classification Variable in a Classification Group and tagging some of the images with the "Test data" variable. Learn how to create a Classification Group and Classification Variable in the Advanced Data Handling section.