Computer Vision Basics Professional Certificate

Computer Vision Basics teaches you how computers extract meaning from images and video. You will begin with the fundamentals every vision engineer needs: how images are stored, colour spaces, filtering, thresholding, edge detection, contours and geometric transformations, using the free OpenCV library in Python.

You will then learn classical feature detection (corners and SIFT keypoints), image alignment and face detection, before moving to modern deep learning: image classification with convolutional networks and transfer learning, object detection with YOLO-style models, and image segmentation. Applied lessons cover video and motion, optical character recognition (reading text from images) and deploying vision models to phones.

Examples come from agriculture, health, transport, conservation and document digitisation in Africa, and the course gives careful attention to privacy and fairness in systems that analyse people. The capstone uses the Beans leaf disease dataset collected in Uganda by the Makerere University AI Lab, combining classical image analysis with a deep learning classifier.

This course is for learners with basic Python skills; some machine learning knowledge helps for Module 4. How the course works: six modules, 23 lessons with more than 30 videos from Computerphile, Columbia University’s First Principles of Computer Vision, DeepLearning.AI, freeCodeCamp and others, hands-on Colab notebooks, a quiz after every module, a capstone project and a final certification examination. Most learners finish in 8 to 10 weeks at 4 hours per week.