Age Verification
DOT functions allow the applicant's age to be verified remotely using biometric functions and identity document data extraction.
Certain businesses require age checks to be performed to establish if the customer or user is permitted by law to enter a business or a website; or to purchase certain goods. Age check, passive liveness, and face matching can be combined to ensure compliance. These checks can be performed in different steps.
Steps in the process
Selfie photo age check
DOT can estimate age (and gender) from the selfie image. This estimate uses neural network models. It outputs a numeric value representing estimated age in years. Passive liveness has to be evaluated as well to prevent spoofs.
Age Verification from Identity Document
If the estimated age is close to the age limit permitted by law, scanning the identity document and extracting the date of birth can calculate the age precisely.
It is recommended to keep a certain tolerance for the estimation. For example, if the age limit is 18, a photo ID should be asked from everybody whose age was estimated under 26 if we want to have a false accept rate of one person per 500. See the tables below.
Age check threshold
The following characteristics have been measured with our testing dataset. Age is returned as an integer number representing years of age.
| FAR level for check <18 yrs | Threshold to ask showing ID |
|---|---|
| 1:100 | <= 24 |
| 1:500 | <= 26 |
| 1:1000 | <= 31 |
| 1:5000 | <= 43 |
| FAR level for check <21 yrs | Threshold to ask showing ID |
|---|---|
| 1:100 | <= 27 |
| 1:500 | <= 28 |
| 1:1000 | <= 36 |
| 1:5000 | <= 43 |
Process Flow
The age verification process is illustrated in the flowchart below:
