Computer Vision

Course description

This course introduces core techniques in computer vision, from image filtering and morphological operations to deep learning-based object detection and segmentation. Students gain practical experience through structured, hands-on exercises emphasizing learning by doing.

Rather than focusing on theory alone, the course is designed around applying concepts directly to real-world images. Students develop the skills to design, implement, and evaluate vision pipelines with both classical and modern approaches.

Course content

Introduction to Digital Images
Thresholding and Filtering
Morphological Operations
Edge and Contour Detection
Image Segmentation
Object Detection with Deep Learning
Image Segmentation with Deep Learning
Multiclass Image Segmentation
Skeleton Analysis
Measuring Objects in Images

Prerequisites

Completion of all Year 1 courses in the Applied Data Science & AI programme.