- Biometrics Research Database Catalog

Details

Biometric Database

Title:

Face Recognition Grand Challenge Data Set - FRGC

Website:

http://www.nist.gov/itl/iad/ig/frgc.cfm

Managing Organization:

National Institute of Standards and Technology

Contributing Organizations:

Country:

United States

Description:

The FRGC data distribution consists of three parts. The first is the FRGC data set. The second part is the FRGC BEE. The BEE distribution includes all the data sets for performing and scoring the six 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).

SubjectsDescription:

The FRGC distribution 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.

SpecialNotes:

The Face Recognition Grand Challenge (FRGC) project has officially ended, however, researchers can still obtain FRGC data for experimentation in their organization. Data and software licenses will need to be signed by legal authorities who are approved to sign licenses on behalf of your organization.

Status:

Active

Access Requirements:

Related Publication:

Back to List

Linked Taxonomies

Modality
- Person
- Friction Ridge
  - Types
    - Friction Ridge Exemplar
      - Two Dimensional (2D)
        
        Live Scan
        
        Type
        
        Optical
        Ultrasonic
        Capacitive
        Thermal
        Not specified
        
        Capture Type
        
        Contact
        Contactless
        Swipe
        Not specified
        
        Livescan certification
        
        PIV-Certified livescan (FAP 10-40)
        Appendix F - Certified livescan (FAP 45-60)
        Uncertified livescan (undefined FAP)
        Not specified
        
        Inked (Non-Live Scan)
        Photographed
        Capture Method
        
        Rolled
        Plain
        Not specified
      - Three Dimensional (3D)
    - Friction Ridge Latent
  - Position
    - Not specified
    - Finger
      - 10 print set (14 images, Position Codes: 1-14)
      - 4 Finger Slap (Position Codes: 13-14)
      - EJI/TIP (Position Code: 19)
      - Unspecified or Unknown Finger (Position Code: 0)
      - Specific Finger(s)
        
        Right Thumb (Position Code: 1)
        Left Thumb (Position Code 6)
        Right Middle (Position Code: 3)
        Left Middle (Position Code: 8)
        Right Index (Position Code: 2)
        Left Index (Position Code: 7)
    - Palm
      - Full Palm (Position Codes: 21,23)
      - Upper Palm (Position Codes: 26,28)
      - Lower Palm (Position Codes: 27,29)
      - Writer's Palm (Position Codes: 22,24)
      - Rolled Palm - Full palm including writer's palm (Position Codes: 83,84)
      - Unknown (Position Code 20)
      - Partial Palm (other palm codes)
      - Not specified
    - Plantar
      - Sole, including toes (Position Codes 61,62)
      - Other sole/toe positions
      - Not specified
  - Resolution
    - 500 ppi
    - 1000 ppi
    - Other resolutions (neither 500 nor 1000 ppi)
    - Not specified
  - Annotations
    - Feature markup
      - Manual feature markup
      - Automated feature markup
- Iris
  - Image Storage Format
    - Unconstrained image size (1)
    - Raw 640 x 480 (2)
    - Cropped (3)
    - Cropped & Masked (7)
    - Not specified
  - Iris Subject Acquisition Profile
    - Iris diameter at least 140 pixels (IAP 20)
    - Iris diameter at least 170 pixels (IAP 30)
    - Iris diameter at least 210 pixels, both eyes captured simultaneously (IAP 40)
  - Acquisition Spectrum
    - Near Infrared
    - Visible full-spectrum (color)
    - Other (defined spectrum)
    - Unspecified
  - Annotations
    - Iris boundaries marked
      - Manual markup
      - Automated markup
- Handwriting
  - Sample Type
    - Handwriting
    - Handprinted
    - Signature
  - Capture Type
    - Static
    - Dynamic
    - Not specified
  - Alphabet
    - Western
    - Non-Western
    - Not specified
- Face
  - Sample Type
    - 2 Dimensional
    - 3 Dimensional
    - Video
  - Position
    - Posed
      - Subject Acquisition Profile
        
        Unknown acquisition profile (SAP 0)
        Surveillance Facial Image (SAP 1)
        Driver's license image (SAP AAMVA) (SAP 10)
        ANSI Full Frontal facial image (SAP 11)
        ANSI Full Frontal Facial image (SAP ANSI 385) (SAP 12)
        ISO Full Frontal facial image (SAP 13)
        ISO Full Frontal Facial Image (SAP ISO/IEC 19794-5) (SAP 14)
        PIV facial image (SAP NIST SP 800-76) (SAP 15)
        Legacy Mugshot (SAP 20)
        Best Practice Application - level 30 (SAP 30)
        Mobile ID Best Practice - Level 32 (SAP 32)
        Best Practice Application 40 (SAP 40)
        Mobile ID Best Practice 42 (SAP 42)
        Best Practice Application - Level 50 (SAP 50)
        Best Practice Application - Level 51 (SAP 51)
        Mobile ID Best Practice - Level 52 (SAP 52)
    - Unposed / Surveillance Facial Image (SAP 1)
    - Not specified / Unknown acquisition profile (SAP 0)
  - Lighting
    - Indoor controlled
    - Indoor uncontrolled
    - Outdoor
    - Not specified
  - Annotations
    - Feature markup
      - Manual feature markup
      - Automated feature markup
- Voice
  - Number of Speakers
    - Single
    - Multiple
    - Not specified
  - Language
    - All English
    - All Non-English
    - Multiple Languages
    - Not specified
  - Transcript Available
Data Type
- Image
  - Image File Format
    - ANSI/NIST-ITL
    - WSQ (500 ppi friction ridge only)
    - JPEG2000
    - Raw image
    - BMP
    - PNG
    - JPEG
    - TIFF
    - Other image formats
    - Not specified
  - Color space
    - Color
    - Grayscale
    - Not Specified
- Video
  - Format
    - RAW
    - 3GP or 3G2
    - Quicktime (QTFF)
    - AVI video format
    - Vorbis (OGG)
    - Windows Media Video (WMV)
    - Advanced Systems / Active Streaming Format (ASF)
    - MPEG-4 (MP4) video format
    - MPEG (MPG)
    - Not specified
  - Sample Type
    - With speech
    - Without speech
    - Not specified
- Audio
  - Format
    - RAW
    - WAV
    - MP3
    - AIFF
    - Windows Media Audio (WMA)
    - NIST Sphere
    - Not specified
- Other
Quality
- Controlled Collection
- Operational Casework
- Arbitrary/In the Wild
- Not specified
Method of Associating Mated Subjects
- Ground truth through controlled collection
- Associated by human examiner
- Associated by automated matcher
- Not specified
Capture
- Mobile/Hand-held
- Fixed
- Not specified
Misc. Data Characteristics
- Subject type
  - Cooperative
  - Actively Uncooperative
  - Unaware/Non-cooperative
  - Not specified
- Subject Demographics
- Longitudinal with age
- Spoof
- Post Mortem

Back to List