Learning path

Computer vision (CV)

Treat images as arrays, then filter, detect edges, threshold, label blobs, and match templates.

About this subject

Computer vision extracts information from images. Classical methods operate directly on arrays of pixels: they filter noise, find edges, separate objects from the background, and locate known patterns. Many of these ideas reappear inside the learned filters of convolutional neural networks.

This path covers images as arrays, convolution filters, Sobel edge detection, Otsu thresholding, connected-component labeling, and template matching, all on tiny images stored as lists. Each lesson uses a small, complete program that runs on its own. Python has the full sequence. The other languages listed below add lessons that use that language's own idioms and standard library, such as Java threads, C++ smart pointers, C# LINQ, or Node.js streams, and appear only for the topics the language supports. The programs are simplified models chosen to make an idea visible, so they are a foundation for further study rather than a replacement for a full course or for production-grade software.

Before you start: Nested lists and loops. The convolution lesson links to the deep-learning path.

1
Python
Readable code for automation, data, and first programs.
Images as arrays of pixels
Represent a grayscale image as rows of numbers, convert color to gray, and adjust brightness with clipping.
Filtering images with convolution
Slide a small kernel over an image to blur it, and compute the valid output size.
Edge detection with the Sobel operator
Estimate intensity gradients with two kernels and combine them into edge strength and direction.
Thresholding with Otsu's method
Pick a threshold automatically by maximizing the separation between dark and bright pixel groups.
Connected-component labeling
Find and number separate blobs in a binary image with a flood fill, and measure their sizes.
Template matching with sum of squared differences
Find where a small pattern occurs in an image by sliding it over every position and scoring the match.
2
C
Learn memory, pointers, and efficient systems programming.
C: smoothing noise with a box-blur convolution
Average each 3×3 neighbourhood of a small image to reduce an isolated bright pixel.
C: grayscale histogram and a global threshold
Count how many pixels have each brightness level and separate dark from bright pixels at the mean.
3
C++
Build fast applications with modern types and classes.
C++: convolution with zero padding
Apply a Laplacian kernel so the output has the same size as the input and responds to a single bright pixel.
C++: grayscale conversion and thresholding
Convert color pixels to brightness with luminance weights and split them into foreground and background.
4
Java
Understand object oriented programs and the JVM.
Java: filtering an image with a convolution kernel
Slide a 3×3 averaging kernel over a small grayscale image to smooth it.
Java: finding edges with the Sobel operator
Estimate the horizontal intensity change at each pixel and mark strong edges.
5
C#
Build typed applications on .NET.
C#: Sobel gradient magnitude on a diagonal edge
Combine horizontal and vertical Sobel responses into one edge-strength value.
C#: the integral image (summed-area table)
Precompute running sums so that the total of any rectangle takes four lookups.
6
JavaScript
Add behavior to the web and build applications.
JavaScript: RGBA pixel arrays and Uint8ClampedArray
Convert pixels stored the way a canvas stores them to grayscale and see how clamping works.
JavaScript: a sharpen filter and why clamping matters
Apply a sharpening kernel to a step edge and see the overshoot clamped to the valid range.
7
TypeScript
JavaScript with static types for dependable code.
TypeScript: a grayscale image class with threshold and flip
Wrap a flat pixel buffer in a class that checks bounds and returns new images from its operations.

About this subject

Python

Images as arrays of pixels

Filtering images with convolution

Edge detection with the Sobel operator

Thresholding with Otsu's method

Connected-component labeling

Template matching with sum of squared differences

C

C: smoothing noise with a box-blur convolution

C: grayscale histogram and a global threshold

C++

C++: convolution with zero padding

C++: grayscale conversion and thresholding

Java

Java: filtering an image with a convolution kernel

Java: finding edges with the Sobel operator

C#

C#: Sobel gradient magnitude on a diagonal edge

C#: the integral image (summed-area table)

JavaScript

JavaScript: RGBA pixel arrays and Uint8ClampedArray

JavaScript: a sharpen filter and why clamping matters

TypeScript

TypeScript: a grayscale image class with threshold and flip