Wait first WTF is Real-time ID checker?
Security is important either offline or online and your best controversial taxi-hailing platform is ensuring you have it safe in their services. Recently rolled out the Realtime Id checker is a tool that ensures your driver is the same as the one who underwent the Uber screening process. In their press release, Uber defined it as “Real-time ID check is our latest security feature that helps us ensure that the driver using the app matches with the account we have on file. Using Microsoft’s Cognitive Services, drivers are periodically asked to share a selfie with Uber in order to log onto the app and start driving. We instantly compare this photo to the corresponding one on file and if the two photos don’t match, the account is temporarily suspended while we look into the matter further. This is just another example of how we explore features to improve the security on the app. ”
Uber has rolled out the update in the following 16 countries — South Africa, Egypt, Russia, Bahrain, UAE, Qatar, India, Singapore, Australia, Indonesia, Chile, Mexico, Brazil, Colombia, Pakistan, and Philippines — on March 13, 2017.
How Real-Time ID Check Works:
- Drivers are asked periodically to take a selfie in the Uber app before they go online and accept rides.
- The photo taken by the driver is then compared to the one already on file with the account.
- If the two photos don’t match, the account is temporarily blocked while Uber representatives will look into the situation.
The Real-time Id checker works in many ways which are safe for you both the driver and the passenger, with a couple of algorithms by the tool you are ensured a known secure ride: With the Microsoft’s Face API wich is not only considered by Uber the most accurate but it also provides them with good features for their update utilizing two specific APIs:
- Face-Detect: Detects human faces in an image and provides additional attributes, such as whether or not the face has glasses. This API is even smart enough to differentiate between reading glasses and sunglasses. This helped us filter out images without a face and improved the match score for verification of the selfies.
- Face-Verify: Compares a face detected from Face-Detect API with an already verified face, and provides a confidence score on whether the two faces belong to the same person or not. Based on the confidence score, we can take appropriate verification action, such as asking the user to retake the selfie.