Learn CV
Help computers find patterns in pixels and video.
Start learning 6 lessons · about 1.5 hours · free
About this track
Explore how computers represent images, separate regions, detect visual patterns, and evaluate predictions. Start from pixel grids, then build toward filters, convolutional neural networks, classification, and object detection. Every lesson includes Python practice that runs in your browser.
Before you start
- No prior computer vision experience needed.
- Basic Python helps; examples introduce the code as you go.
- A modern browser with JavaScript enabled.
- Unit 1 · 0/2 lessons
Image foundations
Represent images as pixel grids and inspect their color channels. Badge: Pixel reader
- 0x001Represent an image as dataConnect image dimensions and pixel values to the arrays a computer can process. 14 min 0/1 exercises solved 14 min 0/1 exercises solved
- 0x102Work with color and image arraysInspect channels, coordinates, and the shape of image data. 14 min 0/1 exercises solved 14 min 0/1 exercises solved
- Unit 2 · 0/2 lessons
Image operations
Segment regions and detect local patterns with filters. Badge: Pattern spotter
- 0x203Separate foreground from backgroundUse a threshold to turn grayscale intensities into a simple binary mask. 14 min 0/1 exercises solved 14 min 0/1 exercises solved
- 0x304Detect patterns with image filtersSee how a small kernel combines neighboring pixels to reveal local patterns. 14 min 0/1 exercises solved 14 min 0/1 exercises solved
- Unit 3 · 0/2 lessons
Vision models and evaluation
Build intuition for CNNs and evaluate model predictions. Badge: Vision builder
- 0x405Build intuition for convolutional networksFollow how local filters and pooling turn pixels into useful image features. 14 min 0/1 exercises solved 14 min 0/1 exercises solved
- 0x506Evaluate predictions and bounding boxesMeasure classification results and compare predicted object regions with ground truth. 14 min 0/1 exercises solved 14 min 0/1 exercises solved
Did you like the lesson? 😆👍
Consider a donation to support our work: