Video Verification API Mode (cloned)

10 min

Introduction

This api takes the image and video as input and gives a score on the basis of which we can tell how much the face in the image matches to the face found in the video. The system has advanced video fraud detection capabilities which eliminate identity theft in user onboarding process. Thus ensuring secure yet simple customer onboardings.

How to call the API

This API receives input as a video file and performs similar analytical actions as our main iframe product

Extract face pictures from the video.
Match face images against the video and give score for each image. This would mean user can give option input of face array. ( To be billed as separate and added to billing of face match API).
Give video quality

API Input Guidelines

Endpoint Details

Endpoints	Environment
https://preproduction.signzy.tech/api/v2/patrons/..your-patron-id../videoforensics	Preproduction
https://signzy.tech/api/v2/patrons/...patronID.../videoforensics	Production

Input Header Parameters

Header Name	Required/Optional	DESCRIPTION
Authorization	Required	access token returned as id field of login request
Content-Type	Required	application/json

Request Body Parameters

PARAMETER NAME	Required/Optional	DESCRIPTION
videoUrl	Required	Input video url (.mp4, .blob, .webm) containing face.
toMatchImage	Required	Face Image which is to be matched against the faces in the video. Supported formats are JPEG, JPG, PNG, PDF. If not passed, face match will not be done.

    {
      "task" : "videoApiMode",
      "essentials" : {
          "toMatchImage" : "...Image Url...",
          "videoUrl" : "...video Url..."
      }
    }

Code Samples

curl --request POST \
  --url https://signzy.tech/api/v2/patrons/....patronid.../videoforensics \
  --header 'Accept: */*' \
  --header 'Accept-Language: en-US,en;q=0.8' \
  --header 'Authorization: <Access-Token>' \
  --header 'content-type: application/json' \
  --data '{"task":"videoApiMode","essentials":{"toMatchImage":"...matchImage url..","videoUrl":"...video url..."}}'

Response Body Parameters

Parameter Name	Description
matchScore	Face match score (0 - 100)
isMatch	Whether face matched or not ( yes or no)
extractedFacesFromVideos	Image urls of faces in the video (first 3 faces based on Depth first search )
videoQualityScore	Quality of video ( 0 - 100)
isVideoValid	Whether video can be accepted (yes or no)

     {
        "essentials": {
            "toMatchImage": "...image url...",
            "videoUrl": "...video url..."
        },
        "id": "...xxxx...",
        "patronId": "...xxxx....",
        "task": "videoApiMode",
        "result": {
            "faceMatch": {
                "matchScore": "...some float value...",
                "isMatch": "no/yes"
            },
            "extractedFacesFromVideos": [
                "...extracted faces image url from video...."                
            ],
            "videoQuality": {
                "VideoQualityScore": "...score between 0-100...",
                "isValid": "yes/no"
            }
        }
      }

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].