Face Comparison
Headers
Header
Value
Content-Type
application/json
Authorization
Model
Kredibel provide two different option of model for face recognition. Every model has its own advantages and disadvantages. We recommend you to try both of the model before deciding which model is the best fit for your case.
1
Model version 1 is the default model used for face recognition task. The model extract 512 facial features (landmarks).
< 0.80: not match >= 0.80: match
2
Model version 2 is the another model option for face recognition task. The model extract 128 facial features (landmarks).
< 0.80: not match >= 0.80: match
Non-Handheld
Endpoint
Method
URL
POST
$vision
/v1/face/verification
Request
Field
Type
Description
image1
<base64:image>
Image binary encoded in base64 without <data:image/png;>. - Supports: JPG, JPEG, PNG - Max Size: 2MB
image2
<base64:image>
Image binary encoded in base64 without <data:image/png;>. - Supports: JPG, JPEG, PNG - Max Size: 2MB
Integer
Model version used to recognize the faces. Default version is 1.
threshold
Float (0-1)
Threshold of the matched faces.
Response
Field
Type
Description
similarity
Float (0-1)
Similarity value between the two images
matched
Boolean
Matched
Handheld
Endpoint
Method
URL
POST
$vision
/v1/face/verification/handheld
Request
Field
Type
Description
image
<base64:image>
Image binary encoded in base64 without <data:image/png;>. - Supports: JPG, JPEG, PNG - Max Size: 2MB
Integer
Model version used to recognize the faces. Default version is 1.
threshold
Float (0-1)
Threshold of the matched faces.
Response
Field
Type
Description
similarity
Float (0-1)
Similarity value between the two images
matched
Boolean
Matched
Errors
Please read this page <Responses & Errors> to know more about response.
Error 4XX
invalid_base64_encoding
Invalid base64 encoding.
false
no_face_detected
No face was detected from one of the images or both images.
true
Error 5XX
For every 5XX http code response, there will be no charge.
Last updated