DataBeginner
Learn how computers understand images, from pixels to crop disease detection, document reading and satellite monitoring. Build practical skills and learn to use computer vision responsibly.
3 modules · 9 lessons · 1 h 50 min
Learn what computer vision is, how images are stored as pixels and numbers, and how models learn visual patterns from examples.
Explore the main tasks of computer vision: classifying images, detecting and segmenting objects, and reading text with OCR.
Plan a real vision project, deploy it in field conditions, and protect privacy and fairness, especially with face recognition.
Computer vision is the part of artificial intelligence that helps computers understand photos and video. It already powers tools that read identity cards, help doctors review medical images, identify plant diseases from phone photos and track drought from satellite images. This course explains, in plain language, how these systems work and where they are useful in Somalia and East Africa.
You will start with pixels and colour, then learn the core tasks of classification, object detection, segmentation and OCR. The final module focuses on practice: collecting good data, running models on phones in the field, and protecting privacy and fairness, especially when systems involve faces. No programming experience is required.
Certificate of completion
Finish every lesson, quiz and assignment to earn your SNAIC certificate.