Design and validation of a line‑scan based AI Vision system for defect detection on a Silicon Belt
Do you want to design and validate an AI Vision system that detects surface defects with micrometer precision? Are you ready to combine line‑scan vision, AI and embedded computing into a graduation‑level industrial solution?

Your assignment
This HBO graduation assignment focuses on the design, implementation and validation of an AI Vision system that detects defects on a Silicon Belt using a Keyence Line Scan camera. The goal is to develop a robust, real‑time detection solution that can be applied in an industrial production environment.

You will start by analysing the Silicon Belt production process and the physical characteristics of dents, such as size, shape and contrast. Based on this analysis, you will define measurable detection requirements and translate them into a technical vision and AI architecture.

The assignment covers the complete engineering lifecycle:

• Problem definition and formulation of a clear research question
• Analysis of line‑scan imaging principles and lighting effects on dent visibility
• Design of a vision pipeline using a Keyence Line Scan camera
• Data collection, preprocessing and annotation of line‑scan image data
• Development and training of AI models for dent detection
• Deployment of the solution on an embedded or industrial computing platform
• Validation and evaluation of detection accuracy, robustness and limitations

The final result is a working prototype supported by a structured graduation report that justifies design choices and evaluates performance using objective criteria.

What makes this assignment unique and fun to do? Why should you choose this assignment?
You will work with professional line‑scan technology as used in high‑end industrial inspection systems. Instead of a generic camera setup, you will experience the challenges of continuous imaging, data throughput and precision defect detection. You are in control of the technical direction and will see your solution running on real hardware with real data.

Your profile
You are currently studying an HBO Bachelor program in a technical field such as:

-Electrical Engineering
-Mechatronics
-Computer Science / ICT
-Applied Artificial Intelligence

You enjoy analysing complex problems and translating them into practical solutions.

To successfully complete this graduation assignment, you have:

-Experience or strong interest in programming (for example Python and/or C/C++)
-Interest in computer vision, machine learning or image processing
-Analytical skills to design experiments and evaluate results
-A structured way of working and the ability to document and justify design choices

You are available for a graduation assignment of 5–6 months, starting around your preferred date, for a minimum of 4 days per week. This assignment is intended as an HBO graduation assignment.

What’s in it for you?

• A challenging assignment with skilled coaching
• Internship/ Graduation compensation of €500,- per month
• Travel cost compensation if you don’t have an ‘OV-weekcard’
• The possibility to network with professionals inside and outside your field of expertise, thanks to our diversity of disciplines which you will work with

Interested?
Are you interested in this assignment? Please click on the button 'apply now' where you can upload your resume and motivation letter. 
If you would like to receive more information concerning this assignment, please contact Erwin Langenhuisen (erwin.langenhuisen@cpp.canon) If you have any questions about the internship in general, please contact Milou Geelen, (+ 31 6 25653192).