H. Drira et al., "An Open Platform for 3D Face Recognition Algorithms", in Proc. of 1st Int. Conf. on 3D Body Scanning Technologies, Lugano, Switzerland, 2010, pp. 229-236, http://dx.doi.org/10.15221/10.229.
An Open Platform for 3D Face Recognition Algorithms
Hassen DRIRA 1, Boulbaba BEN AMOR 1,2, Mohamed DAOUDI 1,2, Anuj SRIVASTAVA 3, Joseph COLINEAU 4
1 LIFL (UMR CNRS 8022), Université de Lille1, France;
2 Institut TELECOM, TELECOM Lille 1, France;
3 Departement of Statistics, FSU, Tallahassee, FL, USA;
4 THALES-TRT, Palaiseau, France
In this paper we describe a new open platform designed to integrate 3D face matching algorithms for recognition. Its main purpose is to provide experimental environment to online operational testing of 3D face recognition approaches, in laboratory conditions. The proposed platform consists of: (i) An acquisition module that interfaces with Minolta 3D laser-based scanner, (ii) A preprocessing sub-system allowing detection and segmentation of the useful part of the face from the depth image (scanner's output) and its processing (iii) A face matching module that incorporates matching algorithms, and (iv) A decision component that provides the final matching result. Moreover, we show an integration example of our algorithm and discuss experimental results. Our 3D facial matching algorithm currently integrated to the proposed platform represents facial surfaces by indexed collections of radial curves on them, emanating from the nose tips, and compares the facial shapes by comparing the shapes of their corresponding curves. Using a framework on elastic shape analysis of curves, we obtain an algorithm for comparing facial surfaces. We also introduce a quality control module which allows our approach to be robust to pose variations and missing data. Comparative evaluation using a common experimental setup on GavabDB dataset, considered as the most expression-rich and noise-prone 3D face dataset, shows that our approach outperforms other state-of-the-art approaches.
3D face matching, face recognition, open platform, preprocessing, geodesics
© Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, www.hometrica.ch.
Reproduction of the proceedings or any parts thereof (excluding short quotations for the use in the preparation of reviews and technical and scientific papers) may be made only after obtaining the specific approval of the publisher. The papers appearing in the proceedings reflect the author's opinions. Their inclusion in these publications does not necessary constitute endorsement by the editor or by the publisher. Authors retain all rights to individual papers.