AI & ML · Ebook

Computer Vision: From Pixels to Perception

by Shriira Press

A comprehensive, self-contained guide to how machines learn to see — to turn raw pixels into understanding: what objects are present, where they are, how a scene is laid out in three dimensions, and what is happening over time. This is the seventh volume in a series; it blends intuition, mathematics, and runnable code, and is the discriminative counterpart to the companion Image Generation book: where that book asks "how do I create an image?", this one asks "how do I understand one?"

Contents

1. 1Preface
2. 2Chapter 1 — What Is Computer Vision?
3. 3Chapter 2 — Images, Pixels, and Formation
4. 4Chapter 3 — Classical Computer Vision
5. 5Chapter 4 — Convolutional Neural Networks for Vision
6. 6Chapter 5 — Image Classification and Architectures
7. 7Chapter 6 — Vision Transformers and Modern Backbones
8. 8Chapter 7 — Object Detection
9. 9Chapter 8 — Semantic and Instance Segmentation
10. 10Chapter 9 — Beyond 2D: Pose, Depth, Motion, and 3D
11. 11Chapter 10 — Self-Supervised and Representation Learning
12. 12Chapter 11 — Video Understanding
13. 13Chapter 12 — Datasets, Evaluation, and Deployment
14. 14Chapter 13 — Ethics: Facial Recognition, Surveillance, and Bias
15. 15Appendix A — Notation and Symbols
16. 16Appendix B — Further Reading