Chexia Face Recognition

Summary

The Face Recognition Algorithm Independent Evaluation (CHEXIA-FACE) is being conducted to assess the capability of face detection and recognition algorithms to correctly detect and recognize children's faces appearing in unconstrained imagery.

Description

2016-JAN-13 – Validation Package now available

The CHEXIA-FACE validation package is now available at https://nigos.nist.gov/chexia-face/chexiafaceValidation.tar.gz. The purpose of validation is to ensure that NIST's execution of your library submission produces the expected output.

The process requires you to

1. compile and link the provided validation code against your libraries,
2. run the executables, and
3. email the results to chexia-face [at] nist.gov (chexia-face[at]nist[dot]gov).

Please see the included README file for more details. NIST will run the same validation code on your submitted libraries and check that the results come out identical. Comments regarding the package should be directed to chexia-face [at] nist.gov (chexia-face[at]nist[dot]gov).

2015-NOV-16 –Final API

The final draft of the C++ API for algorithms and the Participation Agreement are now available.

2015-OCT-05- Draft API

The first draft of C++ API for algorithms is now online. The document is open for public review. Please submit suggestions, comments and questions to chexia-face [at] nist.gov (chexia-face[at]nist[dot]gov), by November 5, 2015.

2015-OCT-05 -Program Announcement

What: The Face Recognition Algorithm Independent Evaluation (CHEXIA-FACE) is being conducted to assess the capability of face detection and recognition algorithms to correctly detect and recognize children's faces appearing in unconstrained imagery.

Who: NIST invites all organizations, particularly universities and corporations, to submit their technologies to CHEXIA-FACE-2016. The evaluation is open worldwide. Participation is free. NIST does not provide funds to participants.

How: CHEXIA-FACE-2016 is a sequestered evaluation of face detection and recognition algorithms. Algorithms are submitted to NIST and executed on large scale corpora available to NIST. The algorithms are submitted as compiled libraries implementing a C++ API. Developers do not submit source code or IP to NIST.

Why: The primary driver of the evaluation is to support forensic investigations of digital media. These images are of interest to NIST's partner law enforcement agencies that seek to employ face recognition in investigating this area of serious crime. The primary applications are identification of previously known victims and suspects, as well as detection of new victims and suspects. The presence of faces may allow a location to be identified or to generate leads.

Important Dates:

Please see the dates on page 2 of the API posted above.

Sponsorship: This work is sponsored by the Department of Homeland Security's Science and Technology Directorate. The CHEXIA-FACE activity falls under their Child Exploitation Image Analytics Program(CHEXIA). NIST is also running a separate evaluation of text recognition technology under the TRAIT 2016.

This work is funded in part by the Department of Homeland Security's Science and Technology Directorate.