Saltar apartados
Universitat d'Alacant


Multimodal Interaction in Pattern Recognition and Computer Vision

Referència: CSD2007-00018
Finançament: Ministerio de Educación y Ciencia
Període: des de 01/10/2007 fins a 09/12/2012
Membres: Calera Rubio, Jorge
Gallego Sánchez, Antonio Javier
Iñesta Quereda, José Manuel
Micó Andrés, María Luisa
Moreno Seco, Francisco
Oncina Carratalá, Jose
Pérez Sancho, Carlos
Pertusa Ibáñez, Antonio Jorge
Ponce de León Amador, Pedro José
Rico Juan, Juan Ramón
Rizo Valero, David
Pérez García, Tomás
Resumen del projecte:Social and industrial demands for Multimodal Interactive (MI) technologies and advanced man-
machine interfaces have dramatically increased in the last decade. While the highly relevant role
of Pattern Recognition (PR) and Computer Vision (CV) in the development of these MI tech-
nologies and interfaces was already foreseen in the early seventies, only a very small fraction of
this huge potential has been exploited so far. Tapping this potential entails several research chal-
lenges and opportunities in order to adapt PR and CV approaches to the dynamic and changing
environments of interactive systems. This project aims to establish a research program to ex-
plore all these opportunities and challenges. In particular, three main oportunities are identified:
a) to take direct advantage of the feedback information provided by the user in each interaction
step to improve raw performance, b) to use feedback-derived data to adaptively (re-)train the
system and tune it to the user behaviour and the specific task considered and c) to acknowledge
the inherent multimodality of interaction to improve overall system behaviour and usability.
Adequate ways to develop these oportunities are presented as a natural evolution of classical
(probabilistic) approaches to PR and CV problems. Based on these approaches, a number of
important applications of MI, PR and CV systems are discussed and a work plan is established
to develop these approaches and applications in a five years time-frame. The ultimate goal is
to show how existing PR and CV technologies can naturally evolve to help the development
of advanced multi-modal interactive systems that will realize the long standing promises of a
seamless synergy between persons and machines. The research consortium that has been consti-
tuted to achieve this goal is composed of 81 highly qualified scientists and engineers from seven
research groups and ten different public research institutions. This staff includes many inter-
nationally renowned researchers in the fields of Pattern Recognition, Machine Learning, Image
Processing, Computer Vision, Speech and Language Processing and Robotics.

Departament de Llenguatges i Sistemes Informàtics

Universitat d'Alacant, carretera Sant Vicent s/n

03690 Sant Vicent del Raspeig, Alacant (Spain)

Tel: (+34) 96 590 3772 | Fax: (+34) 96 590 9326

Segueix-nos en:
[Twitter] [Facebook]