Over Michael
I'm a freelance Computer Vision & AI engineer with over 12 years (6 years professional) of hands-on experience architecting and delivering 30+ vision-driven solutions across industrial, medical, and embedded domains. Specialized in hyperspectral imaging, real-time AI pipelines, 3D vision, computer graphics, rendering, synthetic data, and custom hardware integration. I am a former technical lead in AI and computer graphics as well as a very experienced technical interviewer. For more information check synaptivision.com.
Nederlands
Tweetalig / moedertaal
Engels
Vloeiend
Frans
Beperkte professionele capaciteit
Kan op locatie werken
Tienen (tot 40km)
Werkervaring
- Apixa: Rodent detection in food produceTechnical lead - Computer Vision, AI & Computer GraphicsVOEDSELINDUSTRIEapril 2025 - september 2025 (5 maanden)Leuven, BelgiëDesigned and implemented a computer vision system to detect the presence of rodents in produce before packaging. The project combined high-resolution imaging with custom-trained detection models to identify contaminants in real time at high frame-rates. Developed a workflow that integrated with existing bagging lines, using automated inspection to improve food safety, reduce contamination risks, and ensuring operational efficiency.
- Apixa: Salad mix segmentationTechnical lead - Computer Vision, AI & Computer GraphicsVOEDSELINDUSTRIEfebruari 2024 - juni 2025 (1 jaar en 4 maanden)Leuven, BelgiëDesigned and implemented a segmentation system using synthetic data and hyperspectral imaging to accurately differentiate and classify components in mixed salads. The model enables automated sorting and quality control during the bagging process for grocery stores, improving efficiency and consistency in product packaging.
- Apixa: Indoor Localization and Tracking via RackpolesTechnical lead - Computer Vision, AI & Computer GraphicsLOGISTIEK & SUPPLY CHAINjanuari 2024 - januari 2025 (1 jaar)Leuven, BelgiëDeveloped a computer vision system to detect rackpoles in warehouse images as a precursor for high-precision indoor localization. Worked with a limited dataset affected by significant encoding artifacts, requiring advanced image processing and robust detection methods to reliably identify rackpoles. The solution improved the accuracy of warehouse localization workflows and provided a foundation for tracking systems, despite challenging visual conditions and data limitations.
Aanbevelingen
Wees de eerste die Michael aanbeveelt
Help deze freelancer om te schitteren door te vertellen hoe het is om met hem of haar te werken.
Deze freelancerprofielen matchen ook met zoekopdracht.
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Opleidingen
- Master of Engineering: Computer ScienceKU Leuven2019Specialisation in AI (+took all courses in computer vision and computer graphics.)
- Bachelor in de informaticaKU Leuven2017Minor in business & innovation