▣ ARTIFICIAL INTELLIGENCE · IMAGE PROCESSING

Detect Image Blur API

What it does

Image Blur Detection checks whether an uploaded image is blurry and returns a sharpness score based on Laplacian variance. Send a binary image file, and you get back a boolean blur result plus the values used to make that decision.

Use it when you need to reject low-quality uploads, flag out-of-focus product photos, or gate images before OCR and downstream vision workflows. The response includes blurry, the numeric threshold, a confidence level of low, medium, or high, and laplacian_variance so you can inspect how sharp the image is. Higher Laplacian variance means a sharper image, and the threshold is 100.

This is a straightforward validation step for image pipelines: check capture quality before storage, surface feedback to users, or route blurry images for retake instead of processing them further.

POST

Detect image blur using Laplacian variance and return a sharpness score

https://api.eu.apyhub.com/dosvak/detect-image-blur

QUICKSTART

GUIDE

Quickstart

Upload an image file to check whether it appears blurry.

curl -X POST "https://api.eu.apyhub.com/dosvak/detect-image-blur" \
  -H "apy-token: $APY_TOKEN" \
  -F "file=@/path/to/image.jpg"

What you'll get back

Returns a JSON object with these top-level fields: blurry boolean, threshold integer, confidence string (low, medium, or high), and laplacian_variance number. blurry indicates whether the image is considered blurry; laplacian_variance is higher for sharper images, with a threshold of 100.

{
  "blurry": false,
  "threshold": 100,
  "confidence": "high",
  "laplacian_variance": 243.7
}

TRY ITLIVE · 100 ATOMS

API key

Loading your default key…

The full key is used to call the gateway and stays in this tab — never sent to orbit or saved.

Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.

About this endpoint

What it does

Uploads an image file and analyzes it for blur using Laplacian variance. The response returns a JSON object with blur classification and supporting metrics.

Request Body

Parameter	Type	Mandatory	Description
file	String	Yes	Binary image file to analyze.

Response

Returns a JSON object with four fields: blurry as a boolean, threshold as an integer, confidence as a string enum, and laplacian_variance as a number. Lower variance indicates a blurrier image; the schema notes that the threshold is 100.

Parameter	Type	Mandatory	Description
blurry	Boolean	No	Whether the image is classified as blurry.
threshold	Integer	No	The threshold used for blur classification.
confidence	ENUM	No	Confidence level of the result. Allowed values: `low`, `medium`, `high`.
laplacian_variance	Number	No	The Laplacian variance score. Higher values indicate a sharper image; the schema notes that the threshold is `100`.

Body

Name

Type

Description

bodyREQUIRED

object

—

Max 100MB total per request (all files combined). Larger? Use this API's URL-based endpoint instead, if it has one.

▣ COMMON ERRORS

Errors any endpoint can return

400bad_request

Required parameter missing or malformed body.

401unauthorized

API key missing, revoked, or not authorized for this service.

429rate_limited

Your plan's per-second rate exceeded. Retry with exponential backoff.

503upstream_busy

Backend temporarily unavailable. Try again in a few seconds.