Introduction

In cooperation with IARPA, NIST is currently running three challenges related to processing of unconstrained in-the-wild face images.  These are intended to drive research and development into face detection, verification, identification, and identity clustering.  A secondary goal is to establish definitive evaluation metrics and reporting.

The IARPA Janus Benchmark-B face challenge (IJB-B) defines eight challenges addressing verification, identification, detection, clustering, and processing of crowded images.  This is supported by the IJB-B set of 67000 face images, 7000 face videos, and 10000 non-face images.  

IJB-B has been superseded by IJB-C.