Skip to content
Free public beta until December 4, 2026: every course is open, no card needed. After that, the first chapter of each course stays free and full access is a one-time $39 ($19 for up to 100 founding members chosen for helpful feedback). Your progress is kept. How the beta works

Hu moment

One of seven shape descriptors built from image moments that stay the same under translation, scale, and rotation.

Hu moments are seven specific combinations of an image region's raw and central moments, algebraically constructed so their values stay invariant under translation, uniform scaling, and rotation of the shape -- letting a shape-matching system compare two contours by these seven numbers instead of the underlying pixel boundary.

Examples

  • A wrench's Hu moments come out the same whether it's photographed right-side up, rotated 40 degrees, or shrunk to half its size on the sensor.

See also

image moment contour
Read the full section →
Graph settings

Calculator