🧱 Image Formation Basics

Understanding how images are captured and represented is fundamental to Computer Vision. This guide covers the essentials of image formation, from sensor capture to colour spaces.

---

1. 📷 How an Image is Captured

At its core, a digital image is a grid of light measurements captured by a camera sensor:

• A camera lens focuses incoming light rays onto an image sensor (e.g. CMOS or CCD).
• Each small element on the sensor is called a pixel (picture element).
• During exposure, each pixel measures the light intensity that hits it.

This process yields a 2D matrix of brightness values.

---

2. 🌗 Grayscale Image Formation

A grayscale image records only light intensity—no colour. Each pixel value ranges from 0 (black) to 255 (white), with intermediate values representing shades of grey.

Example (3×3 grayscale image matrix):

[ 34   120  200 ]
[ 45   180  210 ]
[ 90   100  255 ]

Example (single pixel):

Red:   120  
Green:  80  
Blue:   20  

4. 🧰 Other Image Formats (You’ll Encounter Later)

• HSV (Hue, Saturation, Value) — better for colour-based processing
• YCrCb, Lab — used in broadcasting and professional vision pipelines
• Binary — simple two-level (e.g. thresholded) images

---

🔄 Summary

Term	Description
Pixel	Smallest unit of an image
Grayscale	2D matrix of brightness values (0–255)
RGB Image	Stack of three grayscale matrices (R, G & B channels)
Sensor	Hardware that captures light and converts it to data
Resolution	Image dimensions in pixels (e.g. 1920 × 1080)