Fabrizio Beverina

Psychology-Aware video-enabled workplace

The ability to recognize, interpret and express emotions plays a key role in human communication. Current computer interfaces have become able to ”see”, thanks to advanced video sensors and video processing algorithms; however, until recently they could not plausibly ”guess” user intentions, because available feature extraction techniques could not provide the adequate level of service needed to support sophisticated interpretation capabilities. Our approach relies on a set of novel face and posture recognition techniques efficient and robust enough to be at the basis of a fully video-enabled intelligent pervasive workplace, capable of providing value added services based on the real time of facial and postural data. We propose to build on our current work in this area to create an infrastructure for lightweight facial and posture analysis allowing a variety of extended interactions between users and their work, market and entertainment environments.

P300 Off-line Detection: A Fuzzy-based Support System

This article describes the implementation of a fuzzy logic based algorithm for the off-line detection of the so-called P300, an event-related potential signal (ERP) arising when a target stimulus is detected. The algorithm is based on a fuzzy-inferential engine which estimates some parameters on the averaged traces.

CMOS CFA database under varying illumination for benchmarking of face detection algorithms

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.