Computer Vision in Python

First semester 2018

Andrés Marrugo, PhD Universidad Tecnológica de Bolívar

Aims and Scope

This semester course is an introduction to computer vision in Python. It is aimed at graduate students in the Faculty of Engineering. We will focus on the practical aspects of techniques in computer vision with a hands on approach.

At the end of the lectures, one would be able to:

• Understand many different computer vision algorithms and approaches.
• Implement computer vision algorithms for mid-level vision tasks in Python.

Useful Resources

Tutorials, review materials

• Python For Beginners
• Learn Python the Hard Way
• Linear algebra review
• Random variables review

Suggested textbooks

• Solem, Jan Erik. Programming Computer Vision with Python: Tools and algorithms for analyzing images. “ O’Reilly Media, Inc.”, 2012.
• Forsyth, David A., and Jean Ponce. Computer vision: a modern approach. Prentice Hall Professional Technical Reference, 2002.

Outline

This is a new course, this website will be updated as we go along.

Lecture 1: Introduction

We will be discussing the main aspects and motivation for computer vision.

Lecture 2: Image manipulation in Python

We will be discussing the basic .

• Linear filter slides
• Binary images and mathematical morphology

Assignment 1

The goal of this assignment is to get familiarized with Python and basic image manipulations. The assignment is due on 2018-03-02. The assignment should be sent via github classroom:

• Assignment 1

Lecture 3: Local Image descriptors

We will be discussing Harris and SIFT descritors.

Assignment 2

The goal of this assignment is to understand and use local image descriptors. The assignment is due on 2018-03-23. The assignment should be sent via github classroom:

• Assignment 2

Lecture 4: Image to image mappings

We will be discussing 2D to 2D image mappings. Homography, Affine transformations, among others.

• 2D-2D transformations slides
• Alignment slides

Assignment 3

The goal of this assignment is to understand and use image to image mappings. The assignment is due on 2018-04-20. The assignment should be sent via github classroom:

• Assignment 3

Projects

In this course you are required to complete a short project, similar to the assignments, but you are free to choose the approach and the implementation. You will work in teams of two and you will deliver a project report in the IEEE paper format and a 15 minute presentation.

The project is due June 1.

• Project proposals and guidelines
• Upload link