Face recognition is an active area of computer-vision and pattern-recognition research. The Good, the Bad, and the Ugly (GBU) Challenge Problem is a recent effort to build on earlier successful evaluations of face-recognition systems relative to illumination, pose, expression, and age. GBU focuses on “hard” aspects of face recognition from still frontal image pairs that aren’t acquired under studio-like controlled conditions. The image pairs are partitioned into the good (easy to match), the bad (average matching difficulty), and the ugly (difficult to match).
In a paper presented at the 2012 IEEE Workshop on the Applications of Computer Vision (WACV 2012), researchers from the University of Notre Dame investigate image and facial characteristics that can account for the observed significant differences in performance across these three partitions. Their analysis indicates that the differences reflect simple but often ignored factors such as image sharpness, hue, saturation, and extent of facial expressions.
“Predicting Good, Bad and Ugly Match Pairs” and other papers from WACV 2012 are available to both IEEE Computer Society members and paid subscribers via the Computer Society Digital Library.