A parametric representation and feature matching technique for 3D rigid registration: application to 3D face description

Wieme Gadacha; Faouzi Ghorbel

doi:10.1117/12.2064411

16 April 2014 A parametric representation and feature matching technique for 3D rigid registration: application to 3D face description

Wieme Gadacha, Faouzi Ghorbel

Author Affiliations +

Proceedings Volume 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014); 91591K (2014) https://doi.org/10.1117/12.2064411
Event: Sixth International Conference on Digital Image Processing, 2014, Athens, Greece

Abstract

In this communication, a robust, fast and efficient surface registration approach for 3D surfaces is presented. The robusteness of such approach is based on particular features points involved in the process and that make the matching step more precise. Such feature descriptors are extracted from the superposition of two surfacic curves: geodesic levels and radial ones from local neighborhoods defined around reference points already picked on the surface. Moreover, by a generalized version of Shannon theorem, an optimal number of such descriptors points is identified in order to reduce the computational time. Thus, the obtained discretized parametrisation (ordered descriptors) is the basis of the matching phase that becomes obvious and more robust comparing to the classic ICP algorithm. An evaluation of the proposed approach is realized in the mean of complexity time, robusteness of the matching and efficiency. Experimentations are conducted on facial surfaces from the Bosphorus database to estimate the discriminative power in face description.

Citation Download Citation

Wieme Gadacha and Faouzi Ghorbel "A parametric representation and feature matching technique for 3D rigid registration: application to 3D face description", Proc. SPIE 9159, Sixth International Conference on Digital Image Processing (ICDIP 2014), 91591K (16 April 2014); https://doi.org/10.1117/12.2064411

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available