Case study · AI & data science
Optical inspection of circuit boards with AI
Several cameras capture the surface of a circuit board, and AI software detects the conductor tracks and electrical components on it. Built for the mass production of small products.
Project at a glance
- Period
- March to December 2018
- Team
- 4 people: 2 developers, 1 AI specialist, 1 project manager
- Technologies
- Python
- Machine learning for image processing
- Multi-camera setup
- Starting point
- In the mass production of small electronic products, huge numbers of identical circuit boards pass through quality control. At these volumes, visual inspection by people is slow and tiring.
- Senva's role
- Senva developed an automated optical inspection tool for quality control of circuit boards. It uses several cameras, and AI software analyses the images.
- Approach
- The cameras capture the board surface. An ML-based image processing system written in Python detects conductor tracks and electrical components in the images.
- Result
- The result is an inspection tool that automatically detects conductor tracks and electrical components on circuit boards, designed for the mass production of small products.
More case studies
Self-service portal for security products
End users order and manage digital certificates and smartcards themselves. Java, Node.js, Next.js.
Read the case study- 2019
Education data and performance forecasts
Data from an education institute in Vietnam, cleaned, analysed and used for forecasting. Python, scikit-learn, TensorFlow.
Read the case study - 2017
Visual drone detection pilot
For Deutsche Telekom's drone shield programme. A CNN plus classical image recognition.
Read the case study
Intro call
Let's talk about your quality inspection
30 minutes with Kim Pham. We reply within one working day, and sign an NDA beforehand if you wish.
Kim PhamManaging Director, Senva GmbH
- info@senva.de
- Phone
- +49 30 5268 7541
- Address
- Bundesallee 32, 10717 Berlin, Germany