Overview of the Multiple Biometrics Grand Challenge

Abstract

The goal of the Multiple Biometrics Grand Challenge (MBGC) is to improve the performance of face and iris recognition technology from biometric samples acquired under unconstrained conditions. The MBGC is organized into three challenge problems. Each challenge problem relaxes the acquisition constraints in different directions. In the Portal Challenge Problem, the goal is to recognize people from nearinfrared (NIR) and high definition (HD) video as they walk through a portal. Iris recognition can be performed from the NIR video and face recognition from the HD video. The availability of NIR and HD modalities allows for the development of fusion algorithms. The Still Face Challenge Problem has two primary goals. The first is to improve recognition performance from frontal and off angle still face images taken under uncontrolled indoor and outdoor lighting. The second is to improve recognition performance on still frontal face images that have been resized and compressed, as is required for electronic passports. In the Video Challenge Problem, the goal is to recognize people from video in unconstrained environments. The video is unconstrained in pose, illumination, and camera angle. All three challenge problems include a large data set, experiment descriptions, ground truth, and scoring code.

On Using High-Definition Body Worn Cameras for Face Recognition from a Distance

“…Much progress has been made in developing systems to recognise faces in controlled, indoor environments. However, accurate recognition of human faces in unrestricted environments still remains a challenge [10]. This is due to significant intra-class variations caused by changes in illumination, head pose and orientation, occlusion, sensor quality and video resolution [8,9].…”

“…The expectation is that, the recognition accuracy can be improved by increasing the video resolution. Recent studies have shown that using high quality/resolution video result in better face recognition accuracy [1,14,10]. Law-enforcement, forensics, video surveillance and counter-terrorism are areas that can benefit from such biometric systems.…”

Contourlet appearance model for facial age estimation

“…MASM is trained on a set of 500 images of 115 subjects manually annotated with these 68 landmarks and drawn from the National Institute of Standards and Tech nology (NIST) Multiple Biometric Grand Challenge -2008 (MBGC-2008) still face challenge database [22,23], which consists of 34,729 frontal images of 810 subjects. At the fitting stage, the Viola-Jones face detector [27] is used to detect faces in test images and initialize MASM.…”

Variability Compensation Using NAP for Unconstrained Face Recognition

“…Some the recent studies in this field are the Multiple Biometric Grand Challenge (MBGC 2009) [7] and the Face Recognition Vendor Test (FRVT 2006) [8], whose focus of research is shifting to recognizing faces taken under less constrained conditions. As a result of the evolution of this NIST challenges a new competition called GBU has been defined, which consists of three partitions called the Good, the Bad, and the Ugly.…”

“…For the experiments in this paper, we use the segmented datasets provided by MBGC -Multiple Biometric Grand Challenge [7] compressed to 20KB with 120 pixels between the centers of the eyes. The faces were normalized following the ISO norm described in [3], from a size of 408 × 528 to size 168 × 192 pixels.…”