Home

2024 course edition

Second course edition, taught at UNAM in 2024.

Instructors

• instructor: Sébastien Valade (UNAM)
• invited instructor (lecture 10): Ronny Hänsch (TUB)

Lectures

Introduction

• Introduction: slides

Lecture 1: Python & Jupyter crash course

• Lecture: slides
• Tutorial: Python (notebook, notebook slides)
• Tutorial: Jupyter (notebook, notebook slides)

Lecture 2 (CV1): Digital image basics

• Lecture: slides
• Tutorial: Numpy (notebook, notebook slides)
• Exercises: notebook

Lecture 3 (CV2): Filtering

• Lecture: slides
• Exercises: notebook

Lecture 4 (CV3): Morphology & Segmentation

• Lecture: slides
• Exercises: notebook

Lecture 5 (CV4): Homography

• Lecture: slides
• Exercises: notebook

Lecture 6 (CV5): Features & Motion Estimation

• Lecture: slides part 1, slides part 2
• Exercises: notebook

Lecture 7 (ML1): Regression

• Lecture: slides
• Exercises: notebook

Lecture 8 (ML2): Classification part-1

• Lecture: slides
• Exercises: notebook

Lecture 9 (ML3): Classification part-2 (PCA+SVM)

• Lecture: slides
• Exercises: notebook

Lecture 10 (ML4): Random Forests

• Lecture: slides, by Ronny Hänsch

Lecture 11 (DL1): Shallow neural networks (MLPs)

• Lecture: slides
• Exercises: notebook

Lecture 12 (DL2): Deep neural networks (CNNs)

• Lecture: slides
• Exercises: notebook

Lecture 13 (DL3): Custom project & dataset

• Lecture: slides

Recommended Literature

• Alegre, E., Pajares, G., de la Escalera, A. (2016). Conceptos y Métodos en Visión por Computador. CEA
• Szeliski, R. (2021). Computer Vision: Algorithms and Applications (2nd ed.). Springer
• Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras and TensorFlow. O’Reilly Media, Inc.
• James, G., Witten, D., Hastie, T., Tibshirani, R. (2013). An Introduction to Statistical Learning: with Applications in R. Springer
• Chollet, F. (2021). Deep learning with Python. Manning
• Elgendy, M. (2020). Deep learning for vision systems. Manning