omniture

Latest LFW Test Results Announced; PING AN Tech's Face Recognition Technology Receives a High Score

PING AN Tech
2017-02-13 21:01 1846

SHANGHAI, Feb. 13, 2017 /PRNewswire/ -- PING AN Tech's face recognition team recently submitted their test results to the internationally recognized facial recognition technology authority, Labeled Faces in the Wild (LFW). Among the Unrestricted, Labeled Outside Data Results, PING AN Tech was awarded a very high score with a face recognition ratio of 0.9960+/-0.0031, a result that was superior to that of many renowned domestic and foreign rivals. The test results serve as an announcement of the roll out of the technology to the international academic community, and also secures the firm's leading position worldwide in the face recognition market.

(photo source: http://vis-www.cs.umass.edu/lfw/results.html)

Artificial Intelligence (AI) is the way of the future when it comes to social development; and face recognition technology, a core segment of the AI spectrum, is already being used in finance, security and identity recognition applications. During the three years spent on continuous optimization of the application through innovations in technology and confirmation of each iteration through deployments in real use case scenarios, PING AN Tech's face recognition technology was repeatedly used by Ping An Group's business units. The in-house usage yielded several tens of millions of usage instances which provided a constant inflow of test material, creating a virtual closed loop of continuous product improvements. The end product boasts two features that assured the technology's leading position among its peers: rapid identification and a high accuracy rate.

The technology has been applied to 108 use cases involving more than 103 million users, creating a high-precision, easily accessible 100 million+ face database. It is used in high security areas including financial risk control, health insurance, social security benefits programs, railway facility access and airport security. In addition to Ping An's 13 professional companies, the technology has also been successfully deployed by Ping An's 55 partners.

  • The face recognition technology was first used in Ping An Puhui's small loan app Ping An iLoan 2.0. When applying for loans through the app, users can remotely complete identity verification and obtain a loan within no more than 3 minutes by simply activating the camera on their phone, letting the system take a snapshot of the loan applicant's face and archiving the image for authentication. Since the app's launch, the number of "face swiping" transactions has reached 30,000 daily.
  • Using the face recognition technology, Ping An Life Insurance started to provide customer-centric policy services via "face swiping" in 2015, and has constantly improved the customer experience through ongoing simplification of process, while continually upgrading the security features.
  • Since Shenzhen Social Insurance Wallet was launched on June 1, 2016, many hospitals in Shenzhen have adopted Ping An Technology's face recognition technology, marking the beginning of the medical community's adoption of the technology as a routine component of a consultation with one's doctor.

In addressing ongoing concerns over the accuracy and recognition rate of the technology, Liu Fei, Chief Scientist of Artificial Intelligence at PING AN Tech, said, "Face recognition technology is embedded as a module in many complex business processes. It is just one tool among many that should be applied as part of a holistic monitoring system and can only be responsible for its own functionalities within the larger system. When a problem occurs, those not familiar with the technology often attribute the problem to the technology, sometimes confusing the recognition rate with the pass rate or other indicators, leading to misunderstanding. The announcement of the authoritative test results is an effective response to these concerns."

LFW was established in 2007 by the University of Massachusetts 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. Up until now, a few dozen teams from around the globe have provided more than 80 test results. These teams come from companies including Google, Facebook, Microsoft Research Asia, Baidu, Tencent, SenseTime, Face++, Chinese University of Hong Kong and other leading teams from industry and academia. Many of the top ranking methods have played a crucial role in promoting the development of facial recognition technology.

About PING AN Tech

Founded in 2008, PING AN Tech is a wholly-owned subsidiary of Ping An and is headquartered in Shenzhen, with divisions in Beijing, Shanghai, Chengdu and Nanjing. The company has more than 4,000 IT technologists and IT management professionals. The establishment of PING AN Tech was a milestone for Ping An in the IT sector, serving as the announcement of Ping An's foray into the professional IT market and initiating a period of exploration that it has deemed "Technology Leads Finance".

Over the next few years, PING AN Tech, as the high-tech core business and key growth driver of Ping An, will implement the "Technology Leads Finance" roadmap, developing mobile web, cloud and big data applications. PING AN Tech plans on taking the lead in exploring new internet-based business models, by building a leading IT organization, creating a foundation to support the core business, and innovating in collaboration with all business units across the parent company.

To view the original version on PR Newswire, visit:http://www.prnewswire.com/news-releases/latest-lfw-test-results-announced-ping-an-techs-face-recognition-technology-receives-a-high-score-300406108.html

Source: PING AN Tech
collection