Jose Rafael Tena

Learn More
3D Morphable Face Models are a powerful tool in computer vision. They consists of a PCA model of face shape and colour information and allow to reconstruct a 3D face from a single 2D image. 3D Morphable Face Models are used for 3D head pose estimation, face analysis, face recognition, and, more recently, facial landmark detection and tracking. However, they(More)
The ever growing need for improved security, surveillance and identity protection, calls for the creation of evermore reliable and robust face recognition technology that is scalable and can be deployed in all kinds of environments without compromising its effectiveness. In this paper we study the impact that pose correction has on the performance of 2D(More)
Underlying biometrics are biological tissues that evolve over time. Hence, biometric authentication (and recognition in general) is a dynamic pattern recognition problem. We propose a novel method to track this change for each user, as well as over the whole population of users, given only the system match scores. Estimating this change is challenging(More)
The reconstruction of genome-scale metabolic models and their applications represent a great advantage of systems biology. Through their use as metabolic flux simulation models, production of industrially-interesting metabolites can be predicted. Due to the growing number of studies of metabolic models driven by the increasing genomic sequencing projects,(More)
This paper proposes a novel 3D lossy compression algorithm tailored for 3D faces. We analyse the effects of compression on the face verification rate and measure recognition performances on the Face Recognition Grand Challenge database. Whilst preserving the spatial resolution enabling reconstruction of surface details, the proposed scheme achieves(More)
This paper studies how the performance of a 3D face recognition system is affected by compression. A novel lossy compression technique tailored for registered 3D data along with a scheme for 3D face registration and recognition are presented and the results discussed. The proposed scheme achieves a significant compression ratio (factor of 35) without the(More)
  • 1