Automatic quality controls

Manual quality control is often time-consuming and prone to errors. To make this process more objective and faster, more and more manufacturing companies are using computer vision, i.e., automated image processing. Classic algorithms can be used for tasks such as edge detection, while neural networks can be used for more complex tasks.

Neural networks can be used to reliably recognize patterns in images and large data sets. Typical industrial applications include classification tasks, such as automatically classifying components as OK or not OK. In addition to good/bad detection, neural networks can also distinguish between component variants or evaluate surface conditions—quickly, reproducibly, and objectively.