Deep learning checks ampoules: Pharmaceutical quality assurance

Image Processing As Good as the Human Tester

2026-04-29 Source: MVTec Software GmbH | Translated by AI 6 min Reading Time

Related Vendor

Thanks to ongoing technological developments, more and more tasks can be successfully automated with industrial image processing. One particularly demanding task was implemented at the pharmaceutical company Aspen Notre-Dame-De-Bondeville: Filled ampoules have to be inspected for foreign objects. With the help of MVTec Halcon machine vision software and the support of MVTec Customer Services, the goal was achieved: to raise quality assurance to a higher level.

Setup of the automated inspection application: on the left, inspection via machine vision; on the right, the pressure check, i.e. whether the ampoules are correctly sealed.(Image: MVTec) — Setup of the automated inspection application: on the left, inspection via machine vision; on the right, the pressure check, i.e. whether the ampoules are correctly sealed.
(Image: MVTec)

Artificial intelligence is being used more and more frequently in the industrial environment and enables the automation of increasingly demanding activities. Companies benefit from this through significant efficiency gains in various areas. Machine vision in particular is a pioneer here, as large volumes of images are quickly available as training data in the production environment.

Please log in or register and read this article. To be able to read this article in full, you must be registered. Free registration gives you access to exclusive specialist information.

Create My Free Account

Already registered? Log in here