Skip to main content
AI & Machine LearningIntermediate

Computer Vision with OpenCV

Detect objects, recognise faces, and build real-time vision systems.

28 hoursGera AI Tutor4.6 (2,100 learners)

About this course

A hands-on computer vision course using Python and OpenCV. You will learn classical image-processing techniques and modern deep-learning approaches, building projects including a document scanner, a real-time face detection system, and an object classifier using a pre-trained CNN.

Target audience: Developers building vision apps, robotics enthusiasts, ML engineers

What you will learn

  • OpenCV
  • Image processing
  • Object detection
  • YOLO
  • OCR

Course syllabus

10 modules · video + projects

  1. 1Images as arrays: pixels, channels, and colour spaces
  2. 2Filtering, blurring, and edge detection
  3. 3Contours, morphology, and geometric transforms
  4. 4Feature detection: SIFT, ORB, and matching
  5. 5Object detection with Haar cascades and HOG
  6. 6Deep learning for vision: loading and using pre-trained CNNs
  7. 7Real-time video processing with a webcam
  8. 8YOLO for fast object detection
  9. 9Optical character recognition (OCR) with Tesseract
  10. 10Project: licence-plate reader end to end

Prerequisites

  • Python basics
  • NumPy

Frequently asked questions

Do I need a webcam?

A webcam is helpful for the real-time sections but is not required — all exercises can be completed with provided sample videos.

Ready to start Computer Vision with OpenCV?

Join 2,100+ learners already enrolled. Self-paced, certificate on completion.