Accurate recognition

Face Recognition has industry-leading accuracy and is record-breaking in international competitions. It achieved 99.80% accuracy in LFW 2017 and ranked 1st in terms of first-attempt recognition rate (83.29%) in the MegaFace million-scale dataset.

High stability

Face Recognition was tested by Tencent products' massive user base and complex use cases and is proven to be highly reliable and robust with a 99.9% availability rate.

Leading algorithms

Based on the 3rd generation Tencent YouTu Grandmother Model, Face Recognition was optimized by various training methods such as metric learning, transfer learning, and multi-task learning. Its customized fine-tuning or distilling models can meet performance and latency requirements in different use cases.

Ease of use

Face Recognition offers multiple APIs and offline SDKs which enable fast applications and devices integration and satisfy cloud and device demands.

Diverse use cases

Face Recognition is used in a wide variety of use cases such as face recognition access control and attendance, event sign-in, face recognition payment, and face recognition login.

Real-time response

Face Recognition features high concurrence, high throughput, and low latency. It can search and process millions of faces in hundreds of milliseconds, meeting your needs in real time.