Hands-On Computer Vision with Python and OpenCV Training Course

Share this course

Duration

3 Days

Course Overview

Developers who know basic Python build working vision programs in OpenCV over three days of mostly lab time. Day one installs OpenCV with NumPy and Matplotlib and works with images, color spaces such as HSV and simple transforms. Day two covers filtering, binary, adaptive and Otsu thresholding, morphological operations, edge detection and Haar Cascade object detection. Day three trains a k-NN image classifier, tunes it, introduces CNNs and builds real-time face detection from a webcam. Each person finishes by building and presenting a small computer vision application.

Format of Training

  • Brief explanations, then straight into code
  • Many short OpenCV labs, from loading an image to webcam face detection
  • Case studies on retail checkout and face detection in healthcare and security
  • Capstone mini app presented to the group, with questions

Course Objectives

  1. Explain the basics of computer vision and what OpenCV does in image processing.
  2. Handle images and video with OpenCV in Python.
  3. Apply preprocessing steps such as resizing, filtering and thresholding.
  4. Use feature extraction methods like edge detection and contour analysis.
  5. Build image classification models with machine learning.
  6. Create face detection systems with Haar Cascades and deep learning.
  7. Deploy simple computer vision applications in real settings.

Prerequisites

Course Outline

Day 1

Session 1: Introduction to Computer Vision and OpenCV

  • Computer vision explained: main ideas and uses
  • OpenCV: its history, features and installation
  • Getting Python ready with OpenCV, NumPy and Matplotlib

Session 2: Working with Images in OpenCV

  • Loading, showing and saving images
  • Color spaces (RGB, grayscale, HSV) and when to use each
  • Transforms: resizing, rotating, cropping and flipping

Session 3: Hands-on Lab: Basic Image Processing with OpenCV

  • Opening images in OpenCV and changing them
  • Running basic transforms and filters
  • Splitting color channels and converting between color spaces

Day 2

Session 1: Image Preprocessing Techniques

  • Filters for blurring, sharpening and denoising
  • Thresholding methods: binary, adaptive and Otsu’s thresholding
  • Morphological operations: erosion, dilation, opening and closing

Session 2: Hands-on Lab: Image Preprocessing and Filtering

  • Using smoothing and sharpening filters
  • Splitting images into regions with thresholding
  • Cleaning noise with morphological operations

Session 3: Feature Extraction and Object Detection

  • Image features: edges, corners and contours
  • Edge detection with Sobel, Canny and Laplacian filters
  • A first look at object detection with Haar Cascades

Session 4: Hands-on Lab: Object Detection with OpenCV

  • Writing edge detection code
  • Finding objects with Haar Cascades
  • Drawing bounding boxes and picking out several objects in one image

Day 3

Session 1: Image Classification with Machine Learning

  • How image classification works
  • Building a simple classifier with k-Nearest Neighbors (k-NN)
  • A short look at deep learning for classification (basic CNN overview)

Session 2: Hands-on Lab: Image Classification Using Machine Learning

  • Extracting features and preparing data
  • Training an image classifier and scoring it
  • Raising accuracy by tuning parameters

Session 3: Face Detection and Recognition Techniques

  • How face detection works with Haar Cascades
  • Face recognition with deep learning models
  • Where face detection is used in security, healthcare and marketing

Session 4: Hands-on Lab: Face Detection with OpenCV

  • Detecting faces live from webcam input
  • Getting better accuracy with stronger models
  • Practical project: a basic face detection and recognition system

Session 5: Real-World Applications and Project Presentation

  • Case study 1: computer vision in retail (automated checkout, inventory management)
  • Case study 2: face detection in security and healthcare
  • Capstone project: build a mini computer vision application and present it
  • Closing review and advanced topics to explore next

Book This Course

Customise This Course for Your Team

Teams can bring their own image sets so the classifier lab is trained on data they recognize. If face detection is not relevant to your work, day three can swap it for more classification and tuning practice. Tell us what you plan to build after the course.
Need help with the right course to choose?

Explore more opportunities

Introduction to AI and Computer Vision for Business Applications Training Course

Computer Vision Fundamentals: Image Processing and Object Detection Training Course

Hands-On Computer Vision with Python and OpenCV Training Course

Deep Learning for Computer Vision: CNNs, Transfer Learning, and Model Optimization Training Course

AI-Powered Video Analytics and Real-Time Computer Vision Applications Training Course

AI Prompt Engineering Training Course

Hands-On Computer Vision with Python and OpenCV Training Course