Valid

GB/T 41987-2022Public security—Face recognition applications—Test methods for presentation attack detection with fake face (English PDF)

公共安全人脸识别应用防假体呈现攻击测试方法

Preview PDF

This is a limited preview

Buy now to download the full PDF (15 pages)

Need quotation for your management?

Get a formal quotation for GB/T 41987-2022 in 30 minutes.

Issued by

SAMR; SAC

Level / Type

National · Recommended

Issue date

October 14, 2022

Implementation date

May 1, 2023

Scope

GB/T 41987-2022 is the English-translated version of 公共安全人脸识别应用防假体呈现攻击测试方法.

GB/T 41987-2022 describes how to test whether a public-security face recognition system detects a presentation attack made with a fake face.

The tests cover complete face photos, cut-out face photos, face photos with the background removed, electronic photos, face videos, simulated face masks and simulated face head models, in three lighting scenes: indoor, semi-outdoor and outdoor.

Indoors a D50 source is used with uniform illumination not less than 300 lx and not greater than 3000 lx; semi-outdoors halogen lamps are set so that the light intensity where the test object stands is not less than 3000 lx and less than 10000 lx, in side-light, backlight and front-light positions.

A normative annex fixes the basic requirements for the fake-face test samples. It quotes GB/T 41786-2022. Issued on 14 October 2022, it has applied since 1 May 2023.

Found what you need?

Document preview — GB/T 41987-2022

National Standard of the People's Republic of China

ICS: 13.310
Classification: A 91

Issued by: State Administration for Market Regulation; Standardization Administration of the PRC

Preface
1 Scope
2 Normative references
3 Terms and Definitions
4 Test Method
Appendix A (Normative) Basic Requirements for Prosthetic Face Test Samples
Reference

Foreword

This document is in accordance with the provisions of GB/T 1.1-2020 "Guidelines for Standardization Work Part 1: Structure and Drafting Rules for Standardization Documents" drafting.

1 Scope

This document describes a test methodology for protection against prosthetic presentation attacks in facial recognition applications for public safety.

This document is applicable to public safety face recognition system anti-face complete photos, face cut-out photos, face removal background photos, face electronic Tests of attack methods such as photos, face videos, simulated face masks, and simulated face head models.

2 Normative references

The contents of the following documents constitute the essential provisions of this document through normative references in the text. Among them, dated references For documents, only the version corresponding to the date is applicable to this document; for undated reference documents, the latest version (including all amendments) is applicable to this document.

GB/T 41786-2022 Terminology of biometric identification for public security

3 Terms and Definitions

The following terms and definitions defined in GB/T 41786-2022 apply to this document.

3.1 Prosthetic face fakeface

Facial imitation.

Note: Including face photos, face videos, simulated face masks, simulated face head models, etc.

3.2 Live face

Real human faces that come to life.

4 Test methods

4.1 Overview

The lighting environment of the face anti-prosthesis attack test is divided into three scenarios. indoor, semi-outdoor and outdoor. The test samples include full face photos, human Face cutout photos, face removal background photos, face electronic photos, face videos, simulated face masks and simulated face head models.

4.2 Environmental conditions

The ambient light requirements during the test are as follows.

a) Indoor environment simulation. use D50 light source, uniform illumination, light intensity not less than 300lx, not greater than 3000lx.

b) Simulation of semi-outdoor environment (side light, backlight, front light). use halogen lamps, measure with a full-spectrum ordinary illuminance meter, adjust the light source and measure The distance of the test object, so that the light intensity of the area where the test object is located is not less than 3000lx and less than 10000lx. different light rings The positional relationship among the light source, test object and camera in the environment is shown in Figure 1. Under side-lit conditions, the camera, test object and The position of the light source is 90°; under backlight and forward light conditions, the position of the camera, test object and light source are in a straight line.

......
This preview omits tables, figures, formulas and parts of the technical clauses. The complete document — 15 pages — is available in the English PDF.

Referenced standards

Normative references

GB/T 41786-2022Public security—Biometric recognition—Terminology

Cited by

Similar standards

GB/T 31458-2026|GB/T 47478.1-2026|GB 10408-2025|GB 21556.2-2025|GB 46036-2025|GB/T 17001.1-2025

How to Download GB/T 41987-2022

1
Add to cart
Click "Download PDF" on this page and choose "Buy this standard". You can add more standards before checkout.
2
Checkout
Enter your email and billing details. Payment is processed securely by Stripe (cards or bank transfer). Prefer bank details? Request a quotation (min. order $300).
3
Instant delivery (0–9 sec)
Delivery is automatic: within seconds of payment you'll receive an email with a secure download link. The link stays valid for 72 hours.
4
Invoice included
A tax invoice is attached to the confirmation email. Need a custom invoice? Contact us.