Sensing affect: facial analysis and multimodal fusion
The effort of the group has focused in developing a facial affect recognizer able to sense emotions from user's captured facial images. From a set of carefully chosen facial parameters (angles and distances between characteristic points of the face) the system combines in a novel and robust manner five classifiers and performs emotional classification in real-time.
The group has also developed a methodology to deal with the multimodal fusion of affective information coming from different channels over time. The methodology is based on the use of a 2-dimensional evaluation-activation description of affect that goes beyond traditional discrete emotional categories (like Ekman ones) and works in a continuous emotional space (Whissell space). This methodology allows the introduction of novel approaches when sealing with sensing user affect such as “emotional kinematics” and user “emotional paths”.
For more information: http://giga.cps.unizar.es/affectivelab/sensing
The group is collaborating with the Aragon Institute of Technology in the development of Emotracker, a novel tool based on the combination of eye tracking and facial emotional recognition technologies. Emotracker allows the visualization of contents, user emotions and gaze at a glance, and offers a wide range of visualization options, including emotional saccade maps and emotional heat maps. The simultaneous consideration of gaze and emotion opens the door to the evaluation of user engagement, which is of great importance for content creators, but has also other promising fields of application in psychology research and, more specifically, in autism.
More information in:
https://www.ita.es/ita/?servicio&emotracker-herramienta-avanzada-visualizar-afecto-humano (Spanish) and:
NeuroGame aims to study in depth the measurement and analysis of the information associated to the hedonic evaluation of entertainment applications and, more specifically, videogames. The evaluation focus in both the emotional and the cognitive responses with the goal of obtaining a more detailed and precise perspective of User Experience. Members of the AffectiveLab of the University of Zaragoza, the GRIHO group of the University of Lleida, BitBrain Technologies and the Instituto Aragonés de Ciencias de la Salud (Public Health Institute of Aragón) participate in NeuroGame.
© GIGA - Affective Lab | Departamento de Informática e Ingeniería de Sistemas C/ María de
Luna, 1 50015 Zaragoza