Computer Vision — 16-Week Course

Course Description

This course introduces students to the fundamental concepts of computer vision providing an overview of the current methodologies and techniques. Students will explore the theory behind fundamental processing tasks, including segmentation, feature extraction, image classification, and object detection, using a mathematical framework to analyze images as two-dimensional signals. By the end of this course, students will be able to apply the basic principles and tools used in computer vision to solve practical problems in scientific and commercial settings.

Course Objectives

• Explain how light and shading affect the process of image formation.
• Describe human color perception and its computational representation.
• Apply linear filters and perform image convolution operations.
• Implement edge detection algorithms to extract object boundaries.
• Explain the geometry of binocular cameras and apply concepts of 3D reconstruction.
• Compare and evaluate motion detection techniques and their real-world applications.
• Apply a range of image segmentation methods to partition images effectively.
• Select and implement image registration techniques for aligning multiple images.
• Identify key challenges in applying transformations for object recognition.
• Analyze the advantages and disadvantages of various classification methods.
• Develop and implement image enhancement solutions that integrate multiple computer vision techniques.

Textbooks

1. Computer Vision: Algorithms and Applications 2nd Edition Richard Szeliski
2. A Torralba, P Isola, WT Freeman Foundations of Computer Vision (MIT Press)

Assessment & Grading

16-Week Schedule (Topics & Slide Links)

1. Week 1- Welcome! No Slides
2. Week 2 — Introduction to the course Monday Slides Wednesday Slides Wednesday Python code
3. Week 3 — image Filtering Slides
4. Week 4 — Edge Detection Slides_With_speakerNotes