Face Recognition


PhotoFace: Face recognition using photometric stereo


The PhotoFace project covers two EPSRC funded grants that started in April 2007. The aims are as follows:

  1. Use high-speed photometric stereo to rapidly capture facial geometry.
  2. Capture a new 3D face database for testing within the project and for the benefit of the worldwide face recognition research community.
  3. Apply novel and existing state-of-the-art face recognition algorithms to the dataset.
  4. Capture skin reflectance data in order to generate synthetic poses of any face captured by the device.

1. Face reconstruction

The device we have constructed is shown here. The system synchronises either visible or near infrared sources to the camera in high speed. Photometric stereo is then used to deduce a surface normal map that is then integrated into depth.

2. Photoface Database

One area of particular interest was the construction of a database of raw face images. This unique database is very different from existing databases in that it involved data capture of individuals in natural conditions over several months. The Photoface database is available to download for research purposes - please see our 2011 CVPR Workshop paper.

3. Face Recognition

This part of the project aimed to optimise recognition algorithms to the acquired data and considered effects such as

  • the specific reconstruction methods that optimise recognition rates,
  • the inclusion of advanced photometric stereo methods (e.g. to account for shadows and specularities).
  • the choice subspace mapping (PCA, LDA, etc.)

4. Reflectance Analysis

For some applications, it may be useful to compare 3D (or 2.5D) data to 2D images. In these cases it is necessary to use the 2.5D data to render images that have matching illumination conditions to the 2D images. A video illustrating our ability to re-render images in this way can be viewed in either, a greyscale AVI video

or a colour AVI video.

Back to Robot Vision

Theme Leader

Centre for Machine Vision

Professor Melvyn Smith
Bristol Robotics Laboratory,
University of the West of England,
Frenchay Campus, T Building,
Coldharbour Lane,
Bristol, BS16 1QY
Tel: +44 (0)117 32 86358
E-mail: Melvyn.Smith@uwe.ac.uk

Follow the Centre for Machine Vision

Page last updated 12 May 2016