Welcome — start here
Before we begin
If you are new to computer vision, you are in the right place. This course is standalone — you do not need the AI track first, though some ideas overlap (images as numbers, CNNs later).
This page answers questions beginners actually have:
- What is computer vision in plain language?
- What vocabulary will I need (pixel, convolution, ISP, …)?
- How should I read each lesson?
- What does Module 1 cover, and what do I install before the project?
Key concepts (plain English)
Computer vision — Algorithms that take images or video as input and output useful information: labels, boxes, masks, depth, or motion.
Pixel — Smallest picture element; stores one or more numbers (brightness or R, G, B).
Image / tensor — A grid (or grid × channels) of numbers the algorithm reads. Files on disk are decoded into arrays first.
Convolution — Slide a small filter over the image, multiply-and-add at each position. Used for blur, edges, and (in deep learning) feature extraction.
ISP (image signal processor) — Pipeline inside a camera/phone that turns sensor data into the JPEG you see: demosaic, white balance, gamma, noise reduction.
Preprocessing — Resize, normalize, color convert — must match between training and deployment.
Figure
Computer vision at a glance
Figure
Module 1 at a glance
What is this course?
Computer Vision Foundations walks from physics and pixels through geometry, deep learning, segmentation, video, and production deployment — with quizzes and projects in every module.
Module 1 in one sentence
You will understand what a digital image really is (light → sensor → numbers) and how convolution and color prepare data for later algorithms.
| Lesson | Topic |
|---|---|
| 1 | Light, sensors, ISP, noise |
| 2 | Convolution, edges, Canny |
| 3 | Color spaces & preprocessing |
| Quiz | 20 MCQs with review links |
| Project | Imaging pipeline lab in Python |
Before you start
Required: comfort with basic algebra and reading small numeric tables.
Install before the project:
- Python 3.10+
pip install numpy matplotlib opencv-python
Lessons 1–3 are reading + pencil exercises. The project is where you write code.
How to read each lesson
- Read Before we begin and Learning objectives.
- Do checkpoint questions before peeking at answers.
- Skim code only when the lesson says to — Module 1 is mostly intuition.
- After the quiz, use Topics to review links honestly.
Progress saves in this browser when you open a lesson.