Explore pixels, brightness, contrast, thresholding, filters, convolution, edge detection, pooling, and high-dimensional image vectors. Every picture on this page is a numerical array.
Click cells to turn pixels on and off. A tiny image is just a matrix of brightness values.
The same image as numbers. White pixels are 1; black pixels are 0.
These are pixelwise operations: every output pixel depends only on one input pixel.
A filter is a small matrix slid across the image. Each output pixel is a local dot product.
Pooling reduces resolution. Average pooling keeps coarse brightness; max pooling keeps strong activations.
A 32 × 32 image is a point in 1024-dimensional space. Distance between images is vector distance.
Use the interactive tools above, then write short answers.
Prompt 1. Which operations are pixelwise? Which operations use neighborhoods?
Prompt 2. Why is convolution a linear algebra operation?
Prompt 3. Why might pixel distance disagree with human visual similarity?