Bibliography & Resources

Core textbooks, supplementary videos, and reference materials for the course.

The course draws on a curated set of textbooks covering geometry, deep learning, and applied computer vision. All books listed below are either freely available online or have free sample chapters.

Core textbooks

Neural Networks and Deep Learning

Aggarwal, C.C. (2019). Springer. Covers feedforward networks, CNNs, RNNs, and deep learning theory. Free to download via Springer Link.

Deep Learning

Goodfellow, I., Bengio, Y., and Courville, A. (2016). MIT Press. The definitive reference for deep learning fundamentals. Freely available online.

Computer Vision: Algorithms and Applications

Szeliski, R. (2010). Springer. Comprehensive coverage of image formation, feature detection, stereo, recognition, and more. Freely available from the author’s website.

Multiple View Geometry in Computer Vision

Hartley, R. and Zisserman, A. (2004). Cambridge University Press. The standard reference for projective geometry, camera models, and multi-view reconstruction.

Computer Vision for X-ray Testing

Mery, D. and Pieringer, C. (2021). Springer. Written by the course professor. Applies computer vision techniques to non-destructive testing and X-ray inspection.

Computer Vision for X-ray Testing (2015 free sample)

Mery, D. (2015). Free sample PDF of the earlier edition. Useful companion reading for the geometry and reconstruction chapters.

Supplementary reading

• Fairness and Machine Learning — Barocas, Hardt, and Narayanan. Freely available at fairmlbook.org. Required reading for the ethics chapter (Cap04).
• A Tutorial on Fairness in Machine Learning — Practical overview at Towards Data Science.
• MinPlus paper — Mery, D. (CVPRW 2022). Black-box explanation in facial analysis using saliency maps. PDF on CVPR Open Access.
• UNet paper — Ronneberger et al. (2015). The original U-Net segmentation architecture. arXiv PDF.

Supplementary video lectures

All classes from 2021 are available as recorded YouTube lectures. They are listed chapter by chapter below.

Cap00 & Cap01 — Introduction and overview

• Programa del Curso (2021) — Course overview and structure.
• Definiciones, historia, perspectiva (2021) — Definitions, history, and perspective (covers Cap01 sections 1.1 and 1.2).

Cap02 — Computational geometry

• Coordenadas homogéneas, líneas, puntos (2021)
• Python: John Lennon exercise (2021)
• Transformaciones 2D, homografías (2021)
• Transformaciones 3D, perspectiva (2021)
• Python: Rectificación geométrica (2021)
• Estimación de parámetros (2021)
• SIFT features (2021, from Patrones course)
• Python: Calibración (2021)
• Reconstrucción 3D example
• Reconstrucción 3D, calibración (2021)
• Geometría epipolar (2021)
• Python: Geometría epipolar (2021)
• Geometría trifocal, múltiples vistas (2021)

Cap03 — Deep learning

• Introducción a Deep Learning (2021)
• CNN (2021)
• Supplementary CNN video
• Python: CNN exercise (2021)
• YOLO (2021)
• Python: YOLO exercise (2021)
• Análisis facial (2021)
• Python: Reconocimiento facial (2021)
• UNet, GAN, anomaly detection (2021)
• Transformers from scratch — Umar Jamil

Cap04 — Ethics & AI

• Ethics in AI — Ricardo Baeza-Yates
• Fairness, part 1 — Moritz Hardt (MLSS 2020)
• Fairness, part 2 — Moritz Hardt (MLSS 2020)
• Ética en reconocimiento facial (2021)
• Explicabilidad (2021)
• Bias y fairness (2021)
• Adversarial attacks
• Ley 19628 — Chilean data protection law

Historical and contextual references

These resources appear in the history lectures (Classes 2–4) and provide useful background for understanding where computer vision comes from:

• How one-point linear perspective works — Khan Academy explanation of vanishing points.
• The perspective machine — Short video illustrating Dürer’s drawing machine.

Continue exploring

Introduction to Computer Vision

What is computer vision, its history, and the course philosophy.

Course Overview

Full 28-class schedule, chapter structure, and grading.