Computer Vision for Quality Assurance

Surface imperfections & foreign objects

In production, there are irregularities which can be tolerated and others that have to be detected. Shipping material with surface imperfections will result in customer dissatisfaction. Conveying foreign objects to a machine can easily result in severe damages to the machine.

A lot of manual work

Both cases are costly and require extensive quality assurance activities. Today, inspections are often done manually which is not optimal for several reasons. On the one hand, this is often an unfulfilling, repetitive task which still requires high concentration. On the other hand, it comes with high costs, especially as humans can perform such inspection only at a certain rate.

We apply Computer Vision methods to perform such QA tasks. A common scenario is a camera looking at a certain part of a machine or production line. However, our approach is not limited with regard to the sensor but works on several data sources including infra-red cameras, line-scanners, or x-ray technology.

We read in pixel data and compute a decision if the content meets the acceptance criteria or not.

We look at images showing flawless manufactured items as well as at images of different types of defects. Among the methods we apply are classical approaches such as image enhancement or background removal, but also Machine Learning algorithms for object detection and classification.

We have several tools supporting this process, such as ones for annotating test and training data or ones for managing Machine Learning pipelines including evaluation and hyper parameter optimization. In the end, we optimize the learned models for efficient use in production.

Let’s have a look at two specific uses cases.