Foundations
Image Kernels
How a small matrix of weights (a kernel) slides over a larger grid (an image) to compute local features via dot products.
Stage 1 of 4: The Input
Kernel at position 0, computing dot product sum 0
- Input Pixel
An image is just a grid of values. Here, we represent a simple shape using a small 2D array.
Check your understanding
2 questions in the bank. Each attempt draws a fresh set in a fresh order, so a second go is a real second go.
See how small grids of weights slide across an image to detect edges and patterns.
Image Kernels
Before neural networks learn their own filters, traditional computer vision relies on hand-crafted kernels. These small matrices slide across an image to find patterns, like edges or specific textures.
This lab visualizes that mathematical sliding process—the discrete convolution. Watch the dot product update cell by cell to produce a new feature map.
Reference
- Kernel (Filter)
- A small matrix of weights used to extract features
- Feature Map
- The output image produced by the convolution
- Dot Product
- Element-wise multiplication followed by a sum
Break it on purpose
Apply a vertical edge detector to an image with only horizontal lines, resulting in a blank output and proving the filter only activates on specific patterns.