Yitu Tech Wins the 1st Place in Identification Accuracy In Face Recognition Prize Challenge 2017

Yitu Tech (Yitu), a startup company headquartered in Shanghai, and a Chinese pioneer in artificial intelligence and facial recognition technologies, has won the first place in face identification accuracy contest in the first Face Recognition Prize Challenge (FRPC or “the Challenge”) hosted by the Intelligence Advanced Research Projects Activity (IARPA) under the U.S. Office of the Director of National Intelligence.

The victory is a significant milestone for the Chinese AI industry and an endorsement of Yitu’s battle-tested algorithms which excel in recognizing faces from images taken under unconstrained and sometimes extreme conditions. Yitu outperforms more than a dozen well-known international companies in this contest.

Yitu’s algorithms overcome challenges posed by complicated environmental conditions, such as non-frontal head poses, poor and uneven illumination, motion blur, and non-neutral facial expression. The test proceeds by NIST executing participants’ pre-packaged software libraries on images sequestered at NIST. This challenging test dataset contains “non-cooperative” images where subjects were unaware of the camera or, at least, did not engage with, or pose for, the camera under conditions of overexposure, backlight, profile-view face, and distant photography.

The Identification Accuracy Prize winner is determined by considering measurements of identification accuracy. It is stated as False Negative Identification Rate (FNIR) that gives a fixed False Positive Identification Rate (FPIR) no higher than 10^-3.

Algorithms run in a turnkey manner, without tuning, training or other in-the-field specialization, which greatly differs from many academic studies.

“This is a further demonstration of Yitu’s capability and comes on top of our win in Face Recognition Vendor Test (FRVT) this July,” said Dr. Shuang Wu, research scientist at Yitu Tech. “However, having a state-of-the-art algorithm alone is not enough to solve real-world problems, you will need supports from powerful computing infrastructure and sufficiently large dataset. Engineering capability also plays a significant role in performance optimization. Yitu is capable of searching through over a billion records in less than 3 seconds, that showcases our strength in engineering in addition to outstanding algorithms.”

China is quietly leading the world in deploying AI in real-world applications. For instance, Yitu’s facial recognition technologies are adopted by China Merchants Bank to enable face-authenticated cash withdrawals at ATMs in several cities already.

Yitu’s technologies have also being used in wide varieties of application in many industries such as public safety, financial services, healthcare, customs and ports, and integrated marketing. Yitu has formed partnerships with leading companies in these fields, providing integrated solutions.