CMOS CFA database under varying illumination for benchmarking of face detection algorithms
Sara Bocchio, Fabrizio Beverina, Alberto Rosti, L. Castelli, S. Dominelli · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2003
In this paper we present a database containing human faces images, for benchmarking face detection algorithms. Face detection is one of the most critical steps for applications such as recognition, identification, and surveillance. We developed the database systematically, choosing a set of twenty subjects of different gender, performing more acquisitions for each one of them. All faces have different poses and expressions and various characteristics of haircut, beard and accessories. Complex backgrounds and noise conditions reflect the variability of a typical image capture in practical office applications. We performed also experiments of multi-face acquisition. All the subjects are acquired under different illuminants, such as incandescent and halogen lamps, to reproduce realistic indoor environments. The database is a color one, because most face location algorithms are based on skin location, which depends on color identification. For every picture the database contains the full color images in bitmap format and the Color Filter Array (CFA) images with the classic Bayer pattern. We also use this database as a test for our Coupled Metal Oxide Semiconductor (CMOS) sensor, to introduce low cost devices for digital color imaging acquisition and elaboration.