Computer Vision Essentials
How Machines See, From Pixels to Detection
- Pages
- 81
- Chapters
- 43
- Level
- Intermediate
- Format
- E-book
About this book
Computer vision powers phone cameras, factory inspection, medical imaging and self-checkout tills. This book explains how it works and how to build vision systems that hold up in the real world.
You will learn how images are represented, how convolutions extract features, and how networks classify images, detect and segment objects, and recognise text. Later chapters cover vision transformers, transfer learning, data collection and labelling, augmentation, evaluation metrics, and deployment on edge devices, along with the privacy issues that images of people raise.
Worked examples use small numbers you can follow on paper.
What you will learn
- How images become numbers, and why that is hard
- Convolutions, pooling and feature hierarchies
- Classification, detection and segmentation
- Vision transformers and transfer learning
- Data, labelling, augmentation and evaluation
- Deploying vision models and handling privacy
Table of contents
- IntroductionIntroduction
- Chapter 1How Machines See
- Chapter 2Images as Numbers
- Chapter 3Colour Spaces
- Chapter 4Resolution and Resizing
- Chapter 5Classic Image Processing: Filters
- Chapter 6Edges and Gradients
- Chapter 7Convolution, Worked Through
- Chapter 8Convolutional Layers
- Chapter 9Pooling, Stride and Padding
- Chapter 10Feature Hierarchies
- Chapter 11Classic CNN Architectures
- Chapter 12Residual Networks
- Chapter 13Image Classification
- Chapter 14Training Data for Vision
- Chapter 15Labelling Images
- Chapter 16Data Augmentation
- Chapter 17Transfer Learning in Vision
- Chapter 18Evaluating Classifiers
- Chapter 19Object Detection
- Chapter 20Bounding Boxes and IoU
- Chapter 21Non-Maximum Suppression
- Chapter 22Detection Metrics: mAP
- Chapter 23Semantic Segmentation
- Chapter 24Instance Segmentation
- Chapter 25Segmentation Metrics: IoU and Dice
- Chapter 26Keypoints and Pose
- Chapter 27Text in Images: OCR
- Chapter 28Vision Transformers
- Chapter 29Image Embeddings and Search
- Chapter 30Vision–Language Models
- Chapter 31Video Understanding
- Chapter 32Depth and 3D
- Chapter 33Robustness and Distribution Shift
- Chapter 34Bias and Fairness in Vision
- Chapter 35Privacy and Faces
- Chapter 36Deploying on Edge Devices
- Chapter 37Monitoring Vision Systems
- Chapter 38Medical and Scientific Imaging
- Chapter 39Satellite and Aerial Imagery
- Chapter 40Generating and Editing Images
- Chapter 41Case Study: Visual Inspection on a Production Line
- Chapter 42Case Study: Document Processing
- Chapter 43A Project Checklist
- AppendixExercises
- GlossaryGlossary
Who this book is for
Developers, engineers and technical managers who want a solid, practical grounding in computer vision.
Details
| Format | PDF + web edition |
|---|---|
| Length | 81 pages (approx.) |
| Chapters | 43 |
| Level | Intermediate |
| Language | English |
| Topic | Deep Learning |
| Author | Latent Library Editorial |
Keep reading