Biometric face recognition with the highest accuracy: 99.99% in NIST FRVT.
Developed by Oz Forensics specialists, the biometric module incorporates the latest practices in artificial intelligence and is consistently improved by continuous data enrichment. The face recognition algorithm from Oz Forensics achieved one of the best test results in accuracy on the LFW dataset in University of Massachusetts tests in 2020 MIT LFW. The Oz Biometry module allows identifying people with less than 1-second speed and 99.87% accuracy.
Since the beginning of the 2010s, every smartphone has a front camera, making facial biometrics a natural way for authentication. Face biometry can be used both in the registration process and in the process of searching and authentication on large biometric databases.
Facial biometrics are used in the KYC process to compare selfie photos with photographs from documents and confirm the presence of a user in biometric “black” and “white” lists.
Oz Forensics Face Recognition Algorithms allow:
Selfie - Photo from a document or database photo
Comparison of a client's selfie with a photo from a document or from a photo stored in a government database in the process of client identification.
Selfie - Photo previously uploaded to the server
Comparison of the client's selfie with his previously uploaded photo to the server during authentication.
Selfie - Photo base "Blacklist"
Search for matches of the client's selfies in the "Black List" face database to identify fraudsters.
Selfie - Photo base "Safelist"
Search for matches of the client's selfie using the "White List" face database, for example, to determine the VIP person.
What different datasets are tested on?
VISA
Pairs of ISO type images - ISO/IEC 19794-5 Full Frontal. The pose is generally excellent. The image type applies to portraits for passports, driver's licenses, and "mugshot" images. This dataset excludes "mugshot" images.
Only adults' images.
Mugshot
Pairs of ISO type images - ISO/IEC 19794-5 Full Frontal. The pose is generally excellent. The image type applies to portraits for passports, driver's licenses, and "mugshot" images. This dataset includes only "mugshot" photos.
Only USA adults` citizens images.
Visaborder
Pairs of the following images:
the first image - the photo is taken from a web camera. This image is "partially" frontal and is done under the following conditions: different lighting, different angle of head rotation, or partial overlap of the faces;
the second image is ISO type image - ISO/IEC 19794-5 Full Frontal. The pose is generally excellent. The image type applies to portraits for passports, driver's licenses, and "mugshot" images. This dataset excludes "mugshot" images.
Only adults' images.
Wild
Pairs of images that are very unconstrained, with wide yaw and pitch pose variation. Faces can be occluded, including hair and hands.
Only adults' images.
99.87%
ACCURACY
99.9999%
ACCURACY
VISA
99.9919%
ACCURACY
VISABORDER
99.9952%
ACCURACY
MUGSHOT
99.9838%
ACCURACY
BORDER
99.6755%
ACCURACY
WILD
Simple integration
Visual reporting
High precision
Flexibility
Delivery options
Ease-of-use
The pilot project is free of charge.
The cost of implementation in the production loop depends on the individual parameters of your project.
With our flexible licensing terms, you can easily find the right one for you. Get the price within one business day after filling the form here.
Yes, you can. Use one or more platform modules depending on the needs of your business.
1. You can try one of the scenarios of our solution (from the user's point of view) online right now in the web demo section.
2. You can get a personal account to test our solutions' integration into your program code after an online meeting.
We will demonstrate our solutions according to your scenarios and answer your technical questions at the meeting. It will save you time spent on learning technologies.
After the meeting, we will send you the credentials for the demo stand, API, and SDK.
Please leave a request using your corporate email, and our manager will contact you to find a convenient time for a meeting.
3. If you are ready to test and have an application ID, please generate your free trial Mobile SDK license by completing the form.
We provide a trial license for a pilot project for up to 2 months.
We will prepare distributions for your system configuration and provide trial licenses for up to 2 months.
Documentation for our solutions is located here: https://doc.ozforensics.com/oz-knowledge/
With the cloud delivery option, the solution is ready to use. All that remains is to build it into your process.
The on-premise installation of the Oz Forensics platform on your server is completed within one day, and in general, it will take you about 1 hour. We will prepare a personal installer for your system configuration in advance - you need to run it.
The speed of implementing the solution into your workflow depends on the developers on your side. In our experience, this implementation takes no more than one week.
Yes, we are ready to arrange a chat for you with our technical support specialists to help you speed up the testing of our solution. We prefer to use the Slack app for these chats.
Technical support is free during the trial period.
We are not developing a document recognition solution. We use a partner OCR service that is integrated through our API. You can use the service of any other vendor and integrate it yourself through our API.
We are always open to new opportunities for cooperation. We prefer to discuss the details in an online meeting.
Leave a request using your corporate email, and our manager will contact you to find a convenient time for a meeting.
All products include:
Simple,
modularized APIs
Flexible SDKs for iOS,
Android and web
Easy integration
using Docker
Book a demo>
