Skip to content
opencv-wasm

AKAZE features

Algorithm atlasFeatures

Find and describe features in a nonlinear scale space that preserves important boundaries.

Try it on your image ↓

VISUAL WALKTHROUGHFeatures
REFERENCE INPUTTexture and corners

Corners change intensity in more than one direction; a long straight edge is less distinctive.

RESULTA descriptor for one patch

Patch comparisons turn local appearance into a compact signature. This grid illustrates a binary descriptor, not the complete native output.

STEP 03 / 03

Describe oriented patches using the selected descriptor mode.

Illustrative example. The stages explain the method; they are not a live OpenCV execution.

Try it on an image

YOUR IMAGE · REAL OPENCV

Experiment at pixel level

Open full lab ↗

Detect nonlinear scale-space keypoints using AKAZE.

The engine loads on your first run. Your images stay in this browser.

Input448 × 320
OutputWaiting for a result

Scroll over either image to zoom at the pointer. Use the scrollbars to pan both views over the same relative area. Zoom is relative to the input; pixel coordinates belong to each image. Warps can change scene correspondence.

Pixel inspector RGBA · native values · matched scale · 9 × 9 output pixels
Hover to inspect. Click to pin a pixel.
Input 
Select a pixel

Output 
Select a pixel

Sample models and licenses

When to use it

Match objects when an edge-preserving scale representation and compact descriptors are useful.

How it works

  1. 01Build nonlinear diffusion levels.
  2. 02Detect stable responses across those levels.
  3. 03Describe oriented patches using the selected descriptor mode.

nonlinear scale space → keypoints → descriptor

What to tune

threshold affects detector sensitivity; octave settings control scale; descriptor_type selects the representation.

Where it breaks down

Descriptor modes have different output formats and distance metrics. Do not assume every AKAZE configuration produces the same binary descriptor.

TypeScript API

Open an entry for its exact overloads, parameter descriptions, result ownership and pinned upstream source.

xfeatures2d_AKAZEReference →

All of these calls execute on the CPU. Native objects need explicit disposal. See matrices and ownership and build compatibility.

ORB features

Detect oriented corners across an image pyramid and describe them with compact binary tests.

SIFT features

Detect scale-space extrema and describe local gradient distributions around them.

BRISK features

Describe scale-space keypoints using intensity comparisons on concentric sampling rings.

FAST corners

Look for a contiguous arc of brighter or darker pixels around a candidate centre.