Ping An Group
12 May 2017

Ping An Technology Facial Recognition Technology Tops the World in LFW Test Results

Applied 200 Million Times in Over 100 Usage Scenarios

(Hong Kong, Shanghai, 11 May 2017) Ping An Insurance (Group) Company of China, Ltd. (hereafter “Ping An” or the “Group”, HKEx: 2318; SSE: 601318) announced today that, according to the latest published test results from Labeled Faces in the Wild (LFW), the internationally acclaimed facial recognition technology authority, Ping An Technology Facial Recognition Technology was given a face recognition ratio of 98% and the lowest error range, a result that was superior to that of many renowned domestic and foreign rivals. It is also the best results LFW has published and marked a milestone in the success of Ping An Tech AI Lab. Moreover, the Certification Center for the Third Research Institute of the Ministry of Public Security (CSPHS) certified that Ping An Technology Facial Recognition Technology equally received an accuracy rate of 99.84% in test results, and CSPHS has also granted Ping An Technology Facial Recognition Technology a test report certificate.

At present, Ping An Technology Facial Recognition Technology has been applied to more than 100 usage scenarios, involving close to a hundred famous organizations and yielding an application rate of over 200 million times. Chen Liming, General Manager of Ping An Tech, said: “Artificial Intelligence (AI) is the way of the future when it comes to social development. Face recognition technology, a core segment of the AI spectrum, is getting more attention and deployment of usage. With the accumulation of service data, the endorsement of authorities at home and abroad and academic institutions, Ping An Technology Facial Recognition Technology has already attained an internationally leading position.

In order to accurately recognize the face identity, Ping An Tech’s AI Lab makes use of various technical means for image comparison based on the facial features of humans. In the past three years, based on the accumulated user data by Ping An Group's commercial scenarios, Ping An Tech’s AI Lab has continued to carry out thorough study and training on its own with a view to achieving high-accuracy identification and the highest levels in security requirements and stability of use.

Through repeated testing and usage, Ping An Technology Facial Recognition Technology has gradually embraced more and more application scenarios in the business units. In the financial application scenarios, Ping An Tech has successfully launched dozens of projects since 2015, covering credit approval, credit card batch comparison, banking business identity verification, internet account registration, account log in, insurance and underwriting. At present, Shenzhen social security wallet and enterprises including Ping An Puhui, Ping An Bank and Bank of Jiaxing are using Ping An Technology Facial Recognition Technology.

In addition, in terms of the application scenarios in government agencies and institutions, Shenzhen airport and Ping An Technology Facial Recognition Technology achieved a strategic cooperation and have started implementing projects. The Shenzhen Housing Authority and high-speed train identity checking have developed pilot projects and the Beijing-Shanghai High Speed train link is about to formally launch its online application. In Shenzhen, Fujian and Tianjin, the Ministry of Human Resources and Social Security is carrying out pilot testing of facial recognition for its identification documents. The work attendance, door access control of Ping An are also undergoing pilot testing. Ping An Tech is actively expanding into overseas markets and many international financial institutions have shown interest in forming cooperation.

Ping An Tech is proactively developing technologies related to AI in various aspects. Besides face recognition technology, it is committed to making work and life simpler and more intelligent through different kinds of research. Ping An Tech’s audio navigation system covers all of Ping An Group’s telemarketing business and is optimizing the experience of three APP applications — Securities, Mobile Bank and Happy Ping An. Voice print analysis accesses the quality of customer conversation to gauge users’ mood and emotions.


About LFW
LFW was established by the University of Massachusetts in 2007 and is used to evaluate the performance of facial recognition algorithms under unconstrained conditions. It is the most widely used evaluation set in the field of facial recognition. Until now, a few dozen teams around the world have provided more than 80 test results. Such teams come from companies such as Google, Facebook, Microsoft Research Asia, Baidu, Tencent, SenseTime, Face,++ Hong Kong Chinese University and other leading teams from industry and academia. Many of the top-ranked methods have played a crucial role in the development of facial recognition technology.

CSPHS was founded in May, 2015 in accordance with the laws and regulations, such as the Product Quality Law of the People’s Republic of China and Regulations of the People's Republic of China on Certification and Accreditation. Approved by Certification and Accreditation Administration of the People's Republic of China (CNCA) and Ministry of Public Security of the People's Republic of China, directly under the Science and Technology Information Bureau of Ministry of Public Security, it is a professional institution responsible for identifying anti-theft alarm products, physical protection products, road traffic safety products and other social public safety products. CSPHS is a statutory body and an independently operated entity bearing legal liability and responsible for accreditation.


About Ping An Tech

Founded in 2008, Ping An Tech is a wholly-owned subsidiary of Ping An Group. It has more than 4,000 IT technologists and IT management professionals. As the high-tech core business of Ping An Group, Ping An Tech adheres to the roadmap of Technology Leads Finance and continues to develop mobile web, cloud and big data applications. It establishes a leading IT organization, strengthens the foundation to support core business, and takes lead and collaborates with all business units of Ping An to innovate and explore new internet-based business models.

About Ping An

As China’s first joint stock insurance company, Ping An Insurance (Group) Company of China, Ltd. (“Ping An”) is dedicated to becoming a world-leading personal financial services provider. Today, it is an integrated, compact, multi-functional financial services group with services that include insurance, banking, and investment. As at 31 December 2016, the Group had over 1.4 million employees and agents and 130 million individual customers. As at the end of 2016, the Group’s consolidated total assets reached RMB5.58 trillion while equity attributable to shareholders of the parent company stood at RMB383,449 million. Ping An Life and Ping An Property & Casualty are both ranked the second largest in China, Ping An Annuity ranked top in China in their respective areas by premium income. Its subsidiary Ping An Bank is China’s first joint stock bank. The Company’s key areas of business include investment, with subsidiaries such as Ping An Trust, Ping An Securities and Ping An Asset Management. Further, Ping An strives to develop internet finance, including Lufax, Ping An Good Doctor, Ping An Haofang, E-Wallet, Finance One Account. It has achieved significant growth in both the scale and user base of internet finance. As at 31 December 2016, the number of internet users of the Company reached 346 million.

Ping An ranked 20th in Forbes’ 2016 Global 2000, it ranked 41st in Fortune Magazine’s 2016 Global 500 Leading Companies, being 1st among China’s non-state-owned enterprises and the top-ranked China’s insurance companies. Apart from these accolades, Ping An ranked 57th in WPP Millward Brown’s BrandZTM Top 100 Most Valuable Global Brands ranking.

This website uses cookies to help us provide you with better experience and allow us to improve our service. By continuing to browse the site, you understand and agree to our Privacy Policy and Terms of Use .

This website is not supported by IE. Get the latest version of Firefox or Chrome for better browsing experience.