Valid

GB/T 42981-2023Information technology - Biometrics - Test methods for face recognition system (English PDF)

信息技术 生物特征识别 人脸识别系统测试方法

Open the GB/T 42981-2023 preview as PDF

Preview — first pages of GB/T 42981-2023 (full document: 32 pages)

This is a limited preview

Buy now to download the full PDF (32 pages)

Issued by

SAMR; SAC

Level / Type

National · Recommended

Issue date

September 7, 2023

Implementation date

April 1, 2024

Scope

GB/T 42981-2023 is the English-translated version of 信息技术 生物特征识别 人脸识别系统测试方法.

GB/T 42981-2023 gives the test methods for face recognition systems. Vendors quote accuracy figures that are true of the dataset they were measured on and rarely of the deployment, and the number that matters operationally - how often the system accepts the wrong person, and how easily it is fooled by a photograph, a screen or a mask - is not the number usually quoted. The standard fixes how a system is put to the test. It sets the general requirements covering the test environment, the test tools and the test database, then the functional tests - image capture, image analysis, data storage, face comparison, the recognition decision and the management functions - and the performance tests, with an annex giving the test data and the presentation attack detection test methods, the liveness detection performance methods and the indicators and their calculation. It took effect on 1 April 2024.

Document preview — GB/T 42981-2023

National Standard of the People's Republic of China

ICS
35.240.15
Classification
L67

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

Contents

  • 1 Scope1
  • 2 Normative reference documents1
  • 3 Terms and Definitions1
  • 4 Abbreviations1
  • 5 General requirements2
  • 5.1 Overview2
  • 5.2 Test environment2
  • 5.3 Test Tool2
  • 5.4 Test database2
  • 6 Functional test4
  • 6.1 View collection4
  • 6.2 View analysis4
  • 6.3 Data Storage4
  • 6.4 Face comparison5
  • 6.5 Face recognition decision-making6
  • 6.6 Face recognition management6
  • 6.7 Application open interface8
  • 7 Performance Test8
  • 7.1 Technical Test8
  • 27 Reference28

Foreword

This document complies with the provisions of GB/T 1.1-2020 "Standardization Work Guidelines Part

1.Structure and Drafting Rules of Standardization Documents" Drafting. Please note that some content in this document may be subject to patents. The publisher of this document assumes no responsibility for identifying patents. This document is proposed and coordinated by the National Information Technology Standardization Technical Committee (SAC/TC28). This document was drafted by: Shanghai SenseTime Intelligent Technology Co., Ltd., China Electronics Technology Standardization Institute, Beijing Eyes Technology Co., Ltd. Company, Shanghai Yitu Network Technology Co., Ltd., Yuncong Technology Group Co., Ltd., Shanghai Dot and Face Intelligent Technology Co., Ltd., Lenovo Zhongtian Technology Co., Ltd., Shenzhen Yuntian Lifei Technology Co., Ltd., JD Technology Holdings Co., Ltd., and Fuzhou Data Technology Research Institute have Co., Ltd., Rock Jiahua Technology Group Co., Ltd., Shanghai Institute of Measurement and Testing Technology, the Third Research Institute of the Ministry of Public Security, Tongfang Weishi Technology Technology Co., Ltd., Beijing University of Civil Engineering and Architecture, Beijing Zunguan Technology Co., Ltd., Entropy Technology Co., Ltd., National Industrial Information Security Development Exhibition Research Center, Hangzhou Hikvision Digital Technology Co., Ltd., Guangdong Zhongke Zhenheng Information Technology Co., Ltd., Guangzhou Radio and Television Express Gold Rong Electronics Co., Ltd., Xiamen Meiya Pico Information Co., Ltd., iFlytek Co., Ltd., Shenzhen Tencent Computer System Co., Ltd., New World Digital Technology Co., Ltd., Beijing Baidu Network Technology Co., Ltd., Xiamen Entropy Technology Co., Ltd., Beijing Jingmei Technology Co., Ltd., Qingdao Hisense Network Technology Co., Ltd., Huawei Technologies Co., Ltd., Ping An Technology (Shenzhen) Co., Ltd. Company, China Automotive Engineering Research Institute Co., Ltd., Beijing Xiaomi Mobile Software Co., Ltd., CCB Financial Technology Co., Ltd., Shengdian Century Technology Co., Ltd., Shenzhen Jieshun Technology Industrial Co., Ltd., Xiamen Ruiwei Information Technology Co., Ltd., Hangzhou Yufanzhi Energy Technology Co., Ltd., Beijing Pensi Technology Co., Ltd., Zhejiang Dahua Technology Co., Ltd., Beijing University of Posts and Telecommunications, Ant Technology Group Co., Ltd. Co., Ltd., Shandong Haibo Technology Information System Co., Ltd., Yiwu Haoye Network Technology Co., Ltd., Guangdong Haodaitai Technology Group Co., Ltd., Guangdong Bida Security System Co., Ltd., Fujian Haijing Technology Development Co., Ltd., Beijing Jichuang North Technology Co., Ltd. Company, Beijing Shuguang Yitong Technology Co., Ltd., Shanghai Electric Power University, Xi'an Kaihong Electronic Technology Co., Ltd., Guangzhou Aixiang Technology Co., Ltd. Company, Beijing Qingwei Intelligent Technology Co., Ltd., State Grid Blockchain Technology (Beijing) Co., Ltd., Zhongke Vision (Beijing) Technology Co., Ltd., Guangzhou Mailun Information Technology Co., Ltd., Shenzhen Huili Technology Co., Ltd., and Shanghai Zhenliang Intelligent Technology Co., Ltd. The main drafters of this document. Jiang Hui, Zhong Chen, Song Fangfang, Wang Wenfeng, Song Jiwei, Liang Ding, Yang Chunlin, Zhao Chunhao, Wen Hao, Li Jun, Shen Wenzhong, Ning Jing, Su Liwei, Liu Qianying, Wang Zhifang, Wang Qili, Fang Bin, Li Wei, Sun Rongrong, Wang Wu, Cui Jin, Tian Qichuan, Che Lu, Lin Xiaoqing, Liu Yongdong, Zhu Qianqian, Wang Chunmao, Yang Jingfeng, Zhang Lieji, Zhong Min, Wu Ziyang, Mo Bincheng, Sun Shiyou, Qiu Zixiang, Zhang Gang, Chen Shukai, Mei Jingqing, Lu Fanbing, Meng Fanhui, Dai Lei, Yang Nuo, Zhu Yajun, Liao Minfei, Hu Wenmao, Zhao Yong, Jia Baozhi, Zheng Dong, Zhao Lei, Hao Jingsong, Cheng Miao, He Zhaofeng, Lin Guanchen, Han Dongming, Ji Shunjie, Zhou Liang, Yang Shuntian, Lin Feng, Zhang Jinfang, Liu Xuhua, Shao Jie, Xu Jianmin, Yang Sanguo, Wang Bo, Zhao Lihua, Wang Jinqiao, Wang Jin, Qian Chen, Li Hongming, He Bin, Huang Wangjue, Zhou Rong. information technology biometrics Facial recognition system testing method

1 Scope

GB/T 42981-2023 gives the test methods for face recognition systems. Vendors quote accuracy figures that are true of the dataset they were measured on and rarely of the deployment, and the number that matters operationally - how often the system accepts the wrong person, and how easily it is fooled by a photograph, a screen or a mask - is not the number usually quoted. The standard fixes how a system is put to the test. It sets the general requirements covering the test environment, the test tools and the test database, then the functional tests - image capture, image analysis, data storage, face comparison, the recognition decision and the management functions - and the performance tests, with an annex giving the test data and the presentation attack detection test methods, the liveness detection performance methods and the indicators and their calculation. It took effect on 1 April 2024.

This document stipulates the general requirements for face recognition system testing, and describes the functional testing methods and performance testing methods of face recognition systems. and liveness detection testing methods. This document is applicable to third-party inspection and testing institutions that carry out face recognition system testing, development and application of face recognition systems. Carry out testing activities with reference to this document.

2 Normative reference documents

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

GB/T 35273 Information Security Technology Personal Information Security Specifications

GB/T 40660 Basic requirements for biometric information protection in information security technology

GB/T 41772-2022 Technical requirements for information technology biometric face recognition systems

3 Terms and definitions

The terms and definitions defined in GB/T 41772-2022 and the following apply to this document.

3.1 technology testtechnologytest Use pre-collected test data to conduct functional or performance testing of facial recognition systems or components.

3.2 scenario test scenario test Use real test subjects to pass the face recognition system on-site to conduct functional or performance testing.

4 Abbreviations

The following abbreviations apply to this document. FRR False Rejection Rate (FalseRejectionRate)

......
This preview omits tables, figures, formulas and parts of the technical clauses. The complete document — 32 pages — is available in the English PDF.

Referenced standards

Similar standards

How to Buy GB/T 42981-2023

  1. 1Add to cart. Click the "Buy GB/T 42981-2023" button on this page. You can add more standards before checkout.
  2. 2Checkout. Enter your email and billing details. Payment is processed securely by Stripe (cards, Apple Pay, Google Pay supported).
  3. 3Instant 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. 4Invoice included. A tax invoice is attached to the confirmation email. Need a custom invoice? Contact us.

Related Standards

English PDF
32 pages
Instant delivery (0–9 sec)
Invoice included
View Cart

Secure payment via Stripe

Payments accepted

VisaMastercardAmerican ExpressApple PayGoogle PayStripe

GB/T 42981-2023

$590.00

$500.00for partners