Know Your Customer
Liveliness

Face Match

Introduction

Face match API is used to ensure that two images belong to same person/individual. In this we need to either upload two images or give URLs of two images to match ,as input to the API.

You can also provide a optional threshold value between 0.05-0.95 to decide which match is False or True. If match percentage is greater than or equal to threshold then True otherwise False.

It compares two images and gives the ratio of matching between them and matchPercentage between them.

In response, it gives three things as mentioned below

  1. Verified true or false.
  2. A message that says whether the verification completed with positive result or negative result.
  3. A matchPercentage to signify the percentage of match between the two given images.

Face Mask Detection

Signzy is one of the first movers in the industry to develop its proprietary face mask detection solutions which detects if a user is wearing a mask or not during a remote unassisted onboarding use case. It works with our current face match solution and makes GTM faster for our current clientele.

The user flow for face mask detection consists of the following steps

  1. End customer provides a selfie
  2. Client sends the selfie image to Signzy
  3. Signzy detects the mask on the face of the user by identifying facial landmarks on the face
  4. Signzy provides the response to the client that the user is wearing a mask or not with confidence score

Given below are the features of face mask detection that are worth noting:

  1. Accuracy is more than 98%
  2. Platform agnostic as we provide Restful API
  3. Faster response time i.e less than 3 seconds
  4. Secure data storage & purging policy
  5. JPG & PNG images are supported
  6. Max Image size supported is 7 MB

How to call the API

You must first login before sending the request. The authorization header in the request must include the access token obtained from the login API call.

API Input Guidelines

Both firstImage url and secondimage url are Mandatory parameters.

Sample Curl

Production
Preproduction


Input Parameters

PARAMETER NAME

REQUIRED/OPTIONAL

DESCRIPTION

Authorization

REQUIRED

Contains the id parameter returned from the login step

Content-Type

REQUIRED

application/json

firstImage

REQUIRED

URL of the first image to be matched

secondImage

REQUIRED

URL of the second image with which first image to be compared

detectMask

OPTIONAL

In this If image URLs are passed

then the API checks whether the person in the image is wearing

mask or not

Sample Response

JSON


Response Parameters

PARAMETER NAME

DESCRIPTION

firstImage

URL of the first image to be matched

secondImage

URL of the second image with which first image to be compared

detectMask

In this If image URLs are passed then the API checks whether the person in the image is wearing mask or not

faceMatchProvider

Name of the vendor which provides the response

id

Uniqued id of the identity

result

This holds final result parameters of the response.

result.verified

This parameter displays whether the verification done is true/false.

result.message

The message is displayed to the user regarding the status

of the verification.

result.matchPercentage

This parameter displays the match percentage between the two uploaded images

Status Codes

CODE

MESSAGE

400

Invalid Inputs provided

400

Wrong alignHorizontally inputs, please refer docs

400

Only image(s) are allowed, one of the urls does not respond like an image

415

Unsupported file format, check docs



Getting help

Please feel free to contact us if you have any questions, require clarification, or have ideas for how to make the documents or any of our services better.

You can reach out to us at [email protected].