Fast 3D reconstruction and recognition

RODRIGUES, Marcos, ROBINSON, Alan and BRINK, W. (2008). Fast 3D reconstruction and recognition. In: MASTORAKIS, N. E., DEMIRALP, M., MLADENOV, V. and BOJKOVIC, Z., (eds.) Iscgav'08: Proceedings of the 8th Wseas International Conference on Signal Processing, Computational Geometry and Artificial Vision. Recent Advances in Computer Engineering, 1 . WSEAS Press, 15-21.

Full text not available from this repository.
Official URL: http://wseas.us/e-library/conferences/2008/rhodes/...

Abstract

In this paper we discuss methods for 3D reconstruction from a single 2D image using multiple stripe line projection. The method allows 3D reconstruction in 40 milliseconds, which renders it suitable for on-line reconstruction with applications into security, manufacturing, medical engineering and entertainment industries. We start by discussing the mathematical fundamentals of 3D reconstruction and the required post-processing operations in 3D to render the models suitable for biometric applications such as noise removal, hole filling, smoothing and mesh subdivision. The incorporation of data acquired as 3D surface scans of human faces into such applications present particular challenges concerning identification and modelling of features of interest. The challenge is to accurately and consistently find predefined features in 3D such as the position of the eyes and the tip of the nose for instance. A method is presented with recognition rates up to 97% and a preliminary sensitivity analysis is carried out concerning reconstructed and subdivided models.

Item Type: Book Section
Research Institute, Centre or Group - Does NOT include content added after October 2018: Cultural Communication and Computing Research Institute > Communication and Computing Research Centre
Page Range: 15-21
Depositing User: Ann Betterton
Date Deposited: 16 Dec 2010 12:47
Last Modified: 18 Mar 2021 21:15
URI: https://shura.shu.ac.uk/id/eprint/2416

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics