Computer Vision with OpenCV

Course Structure

• Duration: 4 Weeks (Onsite | Online) 

• Onsite Classes: Saturdays 10am - 5pm  (GMT+1) + Extra Weekday Follow-up Practise Sessions 

• Online: Tuesdays & Fridays 5.30pm - 8.00pm  (GMT+1) | Sundays 4.30pm - 8.00pm (GMT+1) 

• Access to the Catalyst AI Hub Africa Alumni Network

• 30 days of post-programme support

• 14 Hands-On Computer Vision Labs

• Projects: 3+ including Real-Time Object Detection System

• Theory vs Practical: 20% / 80%

Ideal For

This course is designed for:

• Developers and engineers who want to build AI-powered image and video analysis systems

• Data scientists with ML experience who want to specialise in visual AI

• Security technology professionals building AI-powered surveillance and monitoring systems

• Agricultural technology developers building crop disease detection and monitoring tools 

• Healthcare professionals working on medical imaging and diagnostic AI systems  

• Technical founders building computer vision products for African markets 

Course Description

Computer vision is one of the most commercially powerful branches of AI — and one of the most in-demand skill sets across Africa today. From intelligent security surveillance and agricultural crop monitoring to retail analytics and medical diagnostic imaging, this course teaches participants to build real-time vision systems using OpenCV and TensorFlow — with every session grounded in African and Nigerian visual data.

Recommended prior knowledge: Comfortable with Python — functions, loops, and basic scripting. Familiarity with NumPy arrays is helpful but not required. No prior computer vision or deep learning experience needed.

Summary of Learning

•      Read, manipulate, transform, and annotate images and video streams using OpenCV — including colour space conversion and batch preprocessing pipelines

•      Apply classical computer vision techniques — Gaussian filtering, Canny edge detection, contour analysis, background subtraction, and optical flow

•      Build, train, and evaluate Convolutional Neural Networks from scratch in TensorFlow for image classification tasks

•      Implement and compare modern CNN architectures including ResNet, MobileNet, and EfficientNet

•      Apply transfer learning and fine-tuning to build high-accuracy image classifiers on small custom datasets

•      Train custom YOLO object detection models on annotated datasets with real-time video stream inference

•      Build face detection and recognition pipelines using deep learning embedding models

•      Deploy a containerised computer vision application to a live cloud endpoint using Docker and FastAPI