Introduction
Computer Vision focuses on enabling machines to interpret and understand visual information. This course introduces the fundamental concepts, techniques, and architectures that power modern vision systems. Participants will explore traditional image-processing methods as well as deep learning–based approaches. Through demonstrations and exercises, learners will see how computer vision models are trained and evaluated. By the end, students will be able to build basic image recognition and object detection systems.
Course Objectives
- Understand image representation and processing
- Learn common computer vision techniques
- Explore CNN-based architectures
- Apply vision frameworks to real tasks
- Build simple vision-based models
Target Audience
- Students entering AI or robotics
- Developers or researchers
- Data scientists needing CV skills
- Engineers working with image data
- Anyone curious about visual AI systems
Course Outline
- 5 Sections
- 0 Lessons
- 5 Days
Expand all sectionsCollapse all sections
- Day 1: Image Fundamentals• Pixels and color spaces
• Image filtering
• Edge detection
• Feature extraction basics
• Hands-on: Image transformations0 - Day 2: Classical Computer Vision• SIFT, SURF, ORB
• Feature matching
• Image segmentation basics
• Optical flow
• Hands-on: Feature extraction0 - Day 3: CNNs for Vision• Convolution and pooling
• Architecture design
• Transfer learning in vision
• Image classification pipeline
• Hands-on: Build a CNN classifier0 - Day 4: Object Detection & Recognition• Bounding boxes
• YOLO and SSD overview
• Detection metrics
• Pre-trained models
• Hands-on: Detect objects in images0 - Day 5: Practical Applications & Ethics• Facial recognition systems
• Medical imaging
• Autonomous vehicles
• Privacy considerations
• Capstone project0
Instructor
Lessons:
