Skip to content
opencv-wasm

Maximally stable extremal regions

Algorithm atlasFeatures

Find connected regions that change little over a range of intensity thresholds.

Try it on your image ↓

VISUAL WALKTHROUGHFeatures
REFERENCE INPUTIntensity-defined regions

The same scene stays here while the working view changes.

RESULTRetain a stable region

The outlined object changes little over a range of thresholds. Stability is about persistence across intensity levels, not a semantic object class.

STEP 03 / 03

Keep regions whose area changes slowly across neighbouring thresholds.

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 ↗

Draw bounding boxes around stable grayscale intensity regions.

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

Detect text-like regions, blobs or stable region features under contrast changes.

How it works

  1. 01Sweep intensity thresholds through the image.
  2. 02Track how connected regions grow and merge.
  3. 03Keep regions whose area changes slowly across neighbouring thresholds.

stability measures relative area change across thresholds

What to tune

delta controls the threshold comparison interval; area and variation settings control retained regions.

Where it breaks down

Stable intensity regions are candidate structures, not recognized characters or objects.

TypeScript API

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

MSERReference →

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.

AKAZE features

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

BRISK features

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