0%
Preparing your experience
English 日本語
0 Start Learning

Your Bag

E-learning materials

Computer Vision using AI

Teach machines to interpret images and video, covering classification, object detection, segmentation, and deploying a working vision model.

Material Overview
Computer Vision using AI

Build computer vision systems with modern tooling. You will handle image data and augmentation, train classifiers using transfer learning, run object detection and segmentation models, and evaluate results with the metrics practitioners actually use. This E-Learning Material also covers optical character recognition, video frame analysis, running models efficiently on edge devices, and the privacy questions that arrive with any camera data.

Curriculum

Learning Path

Each level is enrolled separately. Work through them in order, or start at the level that matches your experience.

  1. Level 01

    Beginner

    Purpose

    Learn how images become data and train your first classifier on a small labelled set.

    Outcome

    You can train an image classifier and read its errors rather than only its accuracy.

    What You'll Learn
    • Understand pixels, colour channels, resizing, and normalisation
    • Build and clean a small labelled image dataset
    • Train an image classifier with transfer learning and review its mistakes

    228 CREDS

  2. Level 02

    Intermediate

    Purpose

    Move from classifying whole images to finding and outlining the objects inside them.

    Outcome

    You can build a detection model and judge its quality with the right metrics.

    What You'll Learn
    • Annotate data for detection and segmentation without wasting effort
    • Train detection models and interpret boxes, scores, and thresholds
    • Evaluate with precision, recall, and intersection over union

    498 CREDS

  3. Level 03

    Advanced

    Purpose

    Handle video, text inside images, and the messy conditions of real camera data.

    Outcome

    You can build a vision pipeline that survives real footage rather than clean sample images.

    What You'll Learn
    • Process video frames with tracking so objects keep an identity over time
    • Extract text from documents and signage with optical character recognition
    • Deal with lighting, occlusion, motion blur, and unusual angles

    701 CREDS

  4. Level 04

    Expert

    Purpose

    Deploy vision models where they run continuously, under constraints of hardware, cost, and privacy.

    Outcome

    You can run a vision system in production that stays accurate, affordable, and lawful.

    What You'll Learn
    • Optimise models for edge devices with quantisation and hardware acceleration
    • Design capture, storage, and retention that respects privacy law
    • Monitor accuracy in the field and retrain as conditions change

    1,066 CREDS