Overview of the FRGC

Not since the mid 1990s has there been such a renewed interest in developing new methods for automatic face recognition. This renewed interest has been fueled by advances in computer vision techniques, computer design, sensor design, and interest in fielding face recognition systems. These techniques hold the promise of reducing the error rate in face recognition systems by an order of magnitude over the Face Recognition Vendor Test (FRVT) 2002 results. The Face Recognition Grand Challenge (FRGC) is being conducted to fulfill the promise of these new techniques.

The primary goal of the FRGC is to promote and advance face recognition technology designed to support existing face recognition efforts in the U.S. Government. FRGC will develop new face recognition techniques and develop prototype systems while increasing performance by an order of magnitude. The FRGC is open to face recognition researchers and developers in companies, academia, and research institutions. FRGC will run from May 2004 to March 2006.

The FRGC consists of a series of two progressively difficult challenge problems. Each challenge problem consists of a data set of facial images and a defined set of experiments. One of the impediments to developing improved face recognition is the lack of data. The FRGC challenge problems include sufficient data to overcome this impediment. The set of defined experiments assists researchers and developers in making progress on meeting the new performance goals.

There are three main contenders for improving face recognition algorithms: high resolution images, three-dimensional (3D) face recognition, and new preprocessing techniques. The FRGC is simultaneously pursuing and will assess the merit of all three techniques. Current face recognition systems are designed to work on relatively small still facial images. The traditional method for measuring the size of a face is the number of pixels between the centers of the eyes. In current images there are 40 to 60 pixels between the centers of the eyes (10,000 to 20,000 pixels on the face). In the FRGC, high resolution images consist of facial images with 250 pixels between the centers of the eyes on average. The FRGC will facilitate the development of new algorithms that take advantage of the additional information inherent in high resolution images.

Three-dimensional (3D) face recognition algorithms identify faces from the 3D shape of a person’s face. In current face recognition systems, changes in lighting (illumination) and pose of the face reduce performance. Because the shape of faces is not affected by changes in lighting or pose, 3D face recognition has the potential to improve performance under these conditions.

In the last couple years there have been advances in computer graphics and computer vision on modeling lighting and pose changes in facial imagery. These advances have lead to the development of new computer algorithms that can automatically correct for lighting and pose changes in facial imagery. These new algorithms work by preprocessing a facial image to correct for lighting and pose prior to being processed through a face recognition system. The preprocessing portion of the FRGC will measure the impact of new preprocessing algorithms on recognition performance.

The FRGC will improve the capabilities of automatic face recognition systems through experimentation with clearly stated goals and challenge problems. Researchers and developers can develop new algorithms and systems that meet the FRGC goals. The development of the new algorithms and systems is facilitated by the FRGC challenge problems.

The FRGC will improve the capabilities of automatic face recognition systems through experimentation with clearly stated goals and challenge problems. Researchers and developers can develop new algorithms and systems that meet the FRGC goals. The development of the new algorithms and systems is facilitated by the FRGC challenge problems.

Structure of the Face Recognition Grand Challenge

The FRGC is structured around two challenge problems, version 1 (ver1) and version 2 (ver2). Ver1 is designed to introduce participants to the FRGC challenge problem format and its supporting infrastructure. Ver2 is designed to challenge researchers to meet the FRGC performance goal.

There are three aspects of the FRGC that will be new to the face recognition community. The first aspect is the size of the FRGC in terms of data. FRGC ver2 contains 50,000 recordings. The second aspect is the complexity of the FRGC. Previous face recognition data sets have been restricted to still images. The FRGC will consist of three modes: high resolution still images, 3D images, and multi-images of a person.

The third new aspect is the infrastructure. The infrastructure for FRGC will be provided by the Biometric Experimentation Environment (BEE), an XML based framework for describing and documenting computational experiments. The BEE will allow the description and distribution of experiments in a common format, recording of the raw results of an experiment in a common format, analysis and presentation of the raw results in a common format, and documentation of the experiment format in a common format. This is the first time that a computational-experimental environment has supported a challenge problem in face recognition or biometrics.

FRGC ver2.0

The FRGC ver2.0 distribution consists of three parts. The first is the FRGC ver2 data set. The second part is the FRGC BEE. The BEE distribution includes all the data sets for performing and scoring the six ver2.0 experiments. The third part is a set of baseline algorithms for experiments 1 through 4. With all three components, it is possible to run experiments 1 through 4, from processing the raw images to producing Receiver Operating Characteristics (ROCs).

The data for FRGC ver2.0 consists of 50,000 recordings divided into training and validation partitions. The training partition is designed for training algorithms and the validation partition is for assessing performance of an approach in a laboratory setting. The validation partition consists of data from 4,003 subject sessions. A subject session is the set of all images of a person taken each time a person’s biometric data is collected and consists of four controlled still images, two uncontrolled still images, and one three-dimensional image. The controlled images were taken in a studio setting, are full frontal facial images taken under two lighting conditions and with two facial expressions (smiling and neutral). The uncontrolled images were taken in varying illumination conditions; e.g., hallways, atriums, or outside. Each set of uncontrolled images contains two expressions, smiling and neutral. The 3D image was taken under controlled illumination conditions. The 3D images consist of both a range and a texture image. The 3D images were acquired by a Minolta Vivid 900/910 series sensor¹.

Ver2.0 consists of six experiments. In experiment 1, the gallery consists of a single controlled still image of a person and each probe consists of a single controlled still image. Experiment 1 is the control experiment. Experiment 2 studies the effect of using multiple still images of a person on performance. In experiment 2, each biometric sample consists of the four controlled images of a person taken in a subject session. For example, the gallery is composed of four images of each person where all the images are taken in the same subject session. Likewise, a probe now consists of four images of a person.

Experiment 3 measures the performance of 3D face recognition. In experiment 3, the gallery and probe set consist of 3D images of a person. Experiment 4 measures recognition performance from uncontrolled images. In experiment 4, the gallery consists of a single controlled still image, and the probe set consists of a single uncontrolled still image.

Experiments 5 and 6 examine comparing 3D and 2D images. In both experiments, the gallery consists of 3D images. In experiment 5, the probe set consists of a single controlled still. In experiment 6, the probe set consists of a single uncontrolled still.

Agency Participation

The FRGC is jointly sponsored by several government agencies interested in improving the capabilities of face recognition technology:

• Federal Bureau of Investigation
• Intelligence Technology Innovation Center
• National Institute of Justice
• National Institute of Standards and Technology
• Technical Support Working Group
• U.S. Department of Homeland Security, Science & Technology

The National Institute of Standards and Technology (NIST) is directing and managing FRGC. The FRGC is also a key component in the face recognition research interagency coordination plan of the National Science & Technology Council’s Subcommittee on Biometrics Research and Development (NSTC Subcommittee on Biometrics R&D). Through the NSTC Subcommittee on Biometrics R&D, activities and results from the FRGC are being shared throughout the federal government.

Researcher Participation in the FRGC

Participation in the FRGC is open to all interested researchers — there is no fee to participate. As of September 2004, the FRGC has 42 participants, including 13 universities, demonstrating an expansive breadth of knowledge and interest in this biometric modality.

If you are interested in participating in the Face Recognition Grand Challenge (FRGC), please contact the FRGC Liaison at frgc@nist.gov.

Requests for access to FRGC ver1.0a will be processed upon receipt of a request by a responsible party at the requesting organization. The responsible party needs to be able to sign licenses on behalf of the organization.

Requests for access to FRGC ver2.0 will be reviewed upon submission of experimental results on FRGC ver1.0a. Results can either be from one of the six challenge experiments or an experiment of the researcher's own design.

Please direct requests for data to the FRGC Liaison at frgc@nist.gov.

More information

• Overview of the Face Recognition Grand Challenge - IEEE Conference on Computer Vision and Pattern Recognition, June 2005
  
  
• FRGC Third Workshop Presentation - FRGC Workshop, February 2005
  
  
• FRGC Presentation - Biometrics Consortium Conference 2004
  
  
• FRGC Presentation - Biometrics Consortium Conference 2005
  
  

¹ The identification of any commercial product or trade name does not imply endorsement or recommendation by the National Institute of Standards and Technology.