Plenary Lecture

Fast 3D Reconstruction and Recognition

Professor Marcos A. Rodrigues
Sheffield Hallam University
Sheffield S1 1WB,
UK
Email: m.rodrigues@shu.ac.uk
 

Abstract: In this presentation we discuss methods for 3D reconstruction from a single 2D shot using multiple stripe line projection. We also present 3D recognition strategies with an application example to 3D face recognition. The technology has been developed and patented within our research group; we start by considering the required 2D image filtering and enhancement and the mathematical fundamentals of 3D reconstruction. 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.
The incorporation of data acquired as 3D surface scans of human faces into applications such as biometry and multimedia present particular challenges concerning identification and modelling of features of interest. The challenge is to accurately and consistently find predefined features such as the corners of the eyes and the tip of the nose for instance. In the field of biometry, if 3D face recognition is to compete with 2D methods, these features must be found to an accuracy greater than 1:1000. In multimedia, the greatest problem occurs with animated 3D faces, where very small inaccuracies are clearly seen in moving faces. These issues will be considered and examples shown on how the technology can be effectively deployed.

Brief Biography of the Speaker:
Professor Marcos A Rodrigues

Academic qualifications:
BEng in Mechanical Engineering (Federal University of Santa Catarina, Brazil)
MSc in Computer Science (The University of Wales, Aberystwyth, UK)
PhD in Computer Science (The University of Wales, Aberystwyth, UK)
Professor of Computer Science (Sheffield Hallam University, Sheffield, UK)

Marcos Aurelio Rodrigues received his BEng in Mechanical Engineering from the Federal University of Santa Catarina (Brazil) in 1983. He was awarded an MSc in Computer Science in 1989 and a PhD in Computer Science in 1991, both from the University of Wales, Aberystwyth.

He has been appointed a Reader in Intelligent Systems within the School of Computing and Management Sciences at Sheffield Hallam University in January 2000 and awarded a Personal Chair in Computer Science in February 2003.

Marcos has published over 140 technical papers in international journals and conferences on the subjects of robotics, computer vision, pattern recognition, systems modelling and artificial intelligence. His main current research interests include 2D and 3D machine vision, machine learning, and pattern recognition.