A system for the 3D reconstruction of the human face using the structured light approach

This paper will describe a computer vision system under development with the aim of use in robust facial recognition applications. The system employs the structured light approach to solve the correspondence problem. The system has been designed with ease of use in mind with calibration procedures designed to be simple enough to be carried out without the use of precision measuring equipment, but robust enough to provide good quality 3D reconstructions. The hardware in use is of consumer grade and is being used in an unmodified form. Early reconstructions of faces based on the projection of a striped pattern have yielded good results with the hope that higher resolution reconstructions will be achieved in the near future.