Skip to content
opencv-wasm

Retina-inspired processing

Algorithm atlasFiltering

Apply a bio-inspired model with separate detail/colour and motion-sensitive processing pathways.

Try it on your image ↓

VISUAL WALKTHROUGHFiltering
REFERENCE INPUTChanging visual input

The retinal model has spatial filters and a temporal state.

RESULTSeparate detail and motion pathways

Parvocellular and magnocellular outputs emphasize different properties; this is a pathway schematic, not simulated retinal output.

STEP 03 / 03

Read the parvocellular and magnocellular pathway outputs.

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 ↗

Process the colour image through the retina model. Parvo preserves detail; Magno measures change after a dark initial frame.

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

Explore local adaptation, dynamic-range compression and transient visual responses.

How it works

  1. 01Apply local adaptation and spatial filtering to the input.
  2. 02Update the model’s temporal state.
  3. 03Read the parvocellular and magnocellular pathway outputs.

input → spatial/temporal adaptation → detail and transient pathways

What to tune

Configure sampling, colour mode and pathway adaptation parameters for the sequence. Reset state deliberately between unrelated clips.

Where it breaks down

Temporal state means consecutive calls are related. The outputs are transformed visual signals, not a calibrated substitute for original intensities.

TypeScript API

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

bioinspired_RetinaReference →

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

Gaussian blur

Replace each pixel with a weighted average that gives nearby pixels more influence.

Box filtering

Average a rectangular neighbourhood with equal weight at every position.

Median filtering

Choose the middle value of a pixel neighbourhood instead of averaging its intensities.

Bilateral filtering

Smooth nearby pixels only when their colours are also similar.