Skip to main content

Blur API Reference

Welcome to the Plate Recognizer Blur API! Use our API to blur license plates and faces in images.
Check detailed instructions on how to install Blur SDK.
Blur forwards images to Snapshot API then uses the detected plate bounding box to perform accurate blurring.


No authentication is required to access Blur API endpoints

Blur Endpoint

POST http://localhost:8001

POST Parameters

uploadYesThe file to be uploaded. optional if upload_url param is present.
upload_urlNoThe url of file to be uploaded. Given priority over upload param.
regionsNoRegions forwarded to Snapshot
skip_regexpNoOverride configuration SKIP_REGEXP. Can be specified multiple times.
facesNoOverride configuration FACES.
platesNoOverride configuration PLATES
logoNoLogo file. If sent, Logo file path is ignored.
logoNoLogo file path. Overrides configuration LOGO
configNoExtends configuration CONFIG.
etNoExclude a percentage margin of image height at the top.
elNoExclude a percentage margin of image width at the left.
ebNoExclude a percentage margin of image height at the bottom.
erNoExclude a percentage margin of image width at the right.
xminNoExcluded region bounding box xmin.
yminNoExcluded region bounding box ymin.
xmaxNoExcluded region bounding box xmax.
ymaxNoExcluded region bounding box ymax.
splitNoSplit image into horizontal chunks before blur. Use on panoramic images
overlapNoOverlap percentage if splitting image. Default is 20.
camera_idNoOverride configuration CAMERA_ID.
snapshot_filenameNoCustom file name sent to Snapshot, Default is the uploaded file name.

Request Format

# Process an image from a URL
curl -o /tmp/blur-car.jpg -d 'upload_url=' -d 'faces=10' -d 'plates=10' http://localhost:8001/

# Get back unskewed bounding box in JSON format and skip burring
curl -d 'upload_url=' http://localhost:8001/

# Download a test picture
curl -o /tmp/car.jpg
# Upload to API for blurring
curl -F 'upload=@/tmp/car.jpg' -o /tmp/blur-car.jpg -F 'faces=10' -F 'plates=10' http://localhost:8001/
# Upload image and logo
curl -F 'upload=@/tmp/car.jpg' -F 'logo=@/tmp/logo.jpg' -o /tmp/blur-car.jpg -F 'faces=10' -F 'plates=10' http://localhost:8001/

# Curl on Windows
curl -X POST -F upload=@car.jpg -o blur-car.png http://localhost:8001/

Response Formats

There are two possible response formats depending on the configuration and request params.

  1. Polygon points around the plates and faces in JSON. This is the default format.
  2. Blurred image if you include faces or plates params or set a blur intensities more than 0 in configuration.

Response Schema

"faces": [
"box": {
"xmax": 326,
"xmin": 300,
"ymax": 137,
"ymin": 100
"score": 0.7088521122932434
"plates": [
"polygon": [
"result": {}
faces/boxFace detection bounding box
faces/scoreFace detection score between 0-1. 0 means low confidence and 1 is the highest confidence
plates/polygonAccurate plate polygon
plates/resultOriginal plate detection result from Snapshot

Error codes

400An error occurred, check response body for more info on the error.

Error Response Schema

{"error":"Invalid Blur intensity. Both faces and plates should not be skipped entirely."}
Floating button icon
CTRL + .