Have you developed software to identity faces in general web photographs? Can your software verify that a face in one photograph is the same as in another? The Intelligence Advanced Research Projects Activity (IARPA), an agency which is part of the Office of the Director of National Intelligence (ODNI), announced the launch of the Face Recognition Prize Challenge (FRPC). The challenge aims to improve biometric face recognition by improving core face recognition accuracy.
IARPA focuses on high-risk, high-payoff research. The Face Recognition Prize Challenge will improve recognition of face images acquired without capture constraints (that is, unconstrained images or images in the “wild”).
The goal of the Face Recognition Prize Challenge is to improve core face recognition accuracy and expand the breadth of capture conditions and environments suitable for successful face recognition. The Challenge comes in two parts:
1) Face identification involves executing one-to-many search to return the correct entry from a gallery, if any; 2) Face verification requires the algorithm to match two faces of the same person while correctly rejecting faces of different persons.
Both tasks involve “non-cooperative” images where subjects were unaware of the camera or, at least, did not engage with, or pose for, the camera.
IARPA says thatthe reason for the competition is the recognition that face recognition is hard. Algorithms are known to commit both false negative and false positive errors, especially when factors such as head pose, illumination, and facial expression depart from formal portrait photograph standards. IARPA is also aware that enormous research has been conducted in recent years with the advent of various deep neural network technologies. IARPA is interested to know whether this rich vein of research has produced advancements in face recognition accuracy.
Registration to join the challenge takes place through this Challenge.gov website. The site directs participants to register with the National Institute of Standards and Technology (NIST) FRPCSupport website. Registration closes on 15 June 2017.
IARPA asks would-be participants to note the following:
— When does the FRPC launch?21 April 2017
— Where to learn about the challenge, including rules, criteria, and eligibility requirements?FRPC rules document
— When does the registration and submission period close?15 June 2017
— Where do participants register?NIST FRPC Support Website
— When do the judges meet to determine winners?September 2017
— When will the winners be announced?October 2017
The challenge proceeds with developers sending pre-compiled software libraries to NIST, which is the designated test laboratory for the FRPC. At NIST the algorithms will be run on sequestered images. This means the FRPC is not an “open-book’’ or “take-home’’ test so neither the test images, nor any training images will be made available to developers.
IARPA notes that the FRPC is intended for prize participants who are eligible to compete for the challenge prizes. IARPA encourages developers of automated face recognition algorithms to participate, both domestic and international, from academia and industry. Other U. S. government agencies, federally funded research and development centers (FFRDCs), university affiliated research centers (UARCs), or any other similar organizations that have a special relationship with the government, that gives them access to privileged or proprietary information, or access to government equipment or real property, will not be eligible to participate in the prize challenge. Entities affiliated with the IARPA Janus program are ineligible to participate.
Read the full rules and challenge eligibility document for the FRPCby downloading this document.
The developers of the most accurate algorithms will be eligible to win cash prizes from a total prize purse of $50,000. Prizes will be distributed for the following criteria:
— One-to-many identification accuracy:$25,000
— One-to-many identification speed:$5,000
— One-to-one verification accuracy:$20,000