Introduction to Computer Vision
Chapter 1: Getting Started with Computer Vision
What is Computer Vision?
How Computers Interpret Images
A Brief History Overview
Common Tasks in Computer Vision
Components of a CV System
Setting Up Your Development Environment
Hands-on: Loading and Displaying an Image
Quiz for Chapter 1
Chapter 2: Digital Image Fundamentals
Pixels: The Building Blocks of Images
Digital Image Representation
Introduction to Color Spaces
Common Image File Formats
Understanding Image Resolution
Image Coordinate Systems
Reading and Writing Image Files
Practice: Exploring Image Properties
Quiz for Chapter 2
Chapter 3: Basic Image Processing Techniques
Point Operations: Brightness Adjustment
Point Operations: Contrast Adjustment
Image Histograms Explained
Histogram Equalization for Contrast Enhancement
Geometric Transformations: Scaling
Geometric Transformations: Rotation and Translation
Introduction to Image Filtering
Basic Smoothing Filters
Hands-on: Applying Basic Image Transformations
Quiz for Chapter 3
Chapter 4: Introduction to Feature Detection
What Are Features in an Image?
Why Detect Features?
Edge Detection Concepts
The Sobel Operator for Edge Detection
The Canny Edge Detector
Corner Detection Concepts
The Harris Corner Detector Idea
Introduction to Feature Descriptors
Hands-on: Detecting Edges in Images
Quiz for Chapter 4
Chapter 5: Introduction to Object Recognition
The Concept of Object Recognition
Template Matching Explained
How Template Matching Works
Limitations of Template Matching
Challenges in Object Recognition
Overview of Machine Learning Approaches
Practice: Simple Template Matching
Quiz for Chapter 5
A Brief History Overview
Was this section helpful?
- Rapid Object Detection using a Boosted Cascade of Simple Features, Paul Viola and Michael Jones, 2001 Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2001), Vol. 1 (IEEE) DOI: 10.1109/CVPR.2001.990517 - This paper introduced the Viola-Jones framework, a real-time object detection system, notably for face detection, which significantly influenced the adoption of computer vision in consumer applications.
- Distinctive Image Features from Scale-Invariant Keypoints, David G. Lowe, 2004 International Journal of Computer Vision, Vol. 60 (Springer) DOI: 10.1023/B:VISI.0000029664.99615.94 - This paper presents the Scale-Invariant Feature Transform (SIFT) algorithm, a method for detecting and describing local features in images, widely used for object recognition and image matching.
- ImageNet Classification with Deep Convolutional Neural Networks, Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, 2012 Advances in Neural Information Processing Systems, Vol. 25 (Curran Associates, Inc.) - This work introduced AlexNet, a deep convolutional neural network that achieved a significant breakthrough in the ImageNet LSVRC-2012 competition, marking the start of the deep learning era in computer vision.