tencent cloud

APIs

DocumentaçãoAPIsFace RecognitionIntroduction

Introduction

Download
Modo Foco
Tamanho da Fonte
Última atualização: 2026-08-12 14:35:04

Overview

Tencent Cloud Shentu Face Recognition is based on Tencent YouTu's powerful face recognition and analysis technology. It provides various features including face detection and analysis, comparison, query, verification, facial feature positioning, and liveness detection, offering developers and businesses a high-performance and high-availability face recognition service. Face recognition has the following advantages:

  • Precise identification: Tencent Cloud face recognition service sets new records across multiple international open competitions. Face comparison achieved an accuracy of 99.80% in the 2017 LFW evaluation, and face search secured the top spot in the MegaFace challenge with a primary recognition rate of 83.29% at million-scale, demonstrating industry-leading identification accuracy.
  • High stability: Tencent Cloud face recognition service has already passed Tencent internal product massive users and complex scenario validation, with stable operation and strong robustness, service availability reachable 99.9%.
  • Leading algorithm: Based on the third-generation Tencent YouTu grandmother model, it optimizes the model through multiple training methods such as metric learning fusion, transfer learning, and multi-task learning. Targeting the characteristics of different scenario-based businesses, it customizes finetuning or distilling models to meet the double requirement for business performance and latency.
  • Easy to use: Provides a variety of APIs and Offline SDKs for rapid embedding into applications and hardware devices, comprehensively meeting cloud and client needs.
  • Diverse use cases: widely used in multi-scenario applications such as face recognition access control attendance, face sign-in, face recognition payment, and face recognition login.
  • Real-time response: Face recognition possesses features such as high-concurrency, high-throughput, and low latency. Even for million-scale face searches, it only takes several hundred milliseconds to be processed, meeting your real-time use requirements.

All face recognition APIs introduced in this chapter comply with the latest OpenAPI 3.0 specification.
You can call APIs to perform operations on face recognition products, such as face detection and analysis, face comparison, face verification, facial feature positioning, and liveness detection.
For all APIs supported by face recognition, please refer to the API overview .

Glossary

For common terminology of the face recognition API interface, see the table below:

Terminology Description
Person library A person library is a collection of face libraries with known identities.
Liveness detection Detect a real-time video recording of a selfie video to confirm the current user is a real person.
Dense key points Perform facial feature positioning (also known as facial keypoint localization) on the requested image to obtain precise information about the human face, returning up to 888 key points for accurate positioning of facial features and facial contour.
Static liveness detection high-precision version Compared with the existing static liveness detection service, the high-precision version maintains a high real person pass rate while enhancing defense capability against attacks such as HD screens, cropped paper, and 3D masks. Its attack interception rate is about 4-5 times that of similar types of products in the industry.
Face verification Facial verification is used to judge whether 'this person' matches the identity of 'this person.' The identity information of 'this person' is already stored in the personnel repository, and there may be multiple face images associated with 'this person.
Face comparison Perform a similarity comparison between the faces in two images and return the similarity score.

Usage Limits

For API parameter limits, refer to the parameter description in each API document.

Getting Started with APIs

You can use the API Explorer tool to call APIs online.
This document bases on face detection and analysis in the face recognition product, and the steps to call the API via the API Explorer Tool are as follows:

  1. After signing up for a Tencent Cloud account and completing real-name authentication, log in to the face recognition console , read and agree to the terms of service, click Enable Now, and you can obtain API interface call permission for face identity verification.
  2. Go to the API Explorer page. For more information about API Explorer tool usage, see Using API Explorer.
  3. Call the IAI api and select face detection and analysis.
  4. After manually inputting the corresponding parameters, perform an online API call to view the response result. For specific input parameter descriptions, please refer to the REST API documentation .
Anterior: HistoryPróximo: API Category

Ajuda e Suporte

Esta página foi útil?

comentários