It sounds so simple! With little effort and training, an artificial intelligence learns to identify product requirements. Scratches, cracks, shape defects and other object errors are detected reliably and without tiring. Subsequently, the respective products can be sorted out before they go to the customer or are further processed. There is no doubt that automated, image-based quality control with artificial intelligence offers many advantages over manual checks by humans or even classic machine vision approaches based on predefined rules. So many benefits - so why is the technology still in the early stages of growth? One of the biggest problems with current AI vision is the lack of experience among users. AI vision technology encompasses so many new methods and subcomponents that companies—especially small midsize companies—often don’t know which ones are suitable for them. Often they do not have the time, manpower or courage at all to evaluate the new technology in detail in all its facets.

There is also often the question of whether AI vision is even suitable for a particular task or can solve it. Unfortunately, this hen-egg problem too often leads to the technology not being evaluated at all. Certainly, the technology still has to mature, especially in the industrial environment, in order to reach an acceptance level like the proven classical image processing methods. On the other hand, there are already user-friendly software tools that enable even users without experience to evaluate their applications with AI vision and implement them intuitively.