01-06-2012, 04:26 PM
Three-Dimensional Face Recognition Using Surface Space Combinations
3DFaceRecUsingSurfaceSpaceCombinations-BMVC.pdf (Size: 341.72 KB / Downloads: 28)
Introduction
Despite significant advances in face recognition technology, it has yet to achieve levels
of accuracy required for many commercial and industrial applications. The high error
rates stem from well-known sub-problems. Variation in lighting, facial expression and
orientation all significantly increase error rates. In an attempt to address these issues,
research has begun to focus on the use of three-dimensional face models, motivated by
three main factors. Firstly, relying on geometric shape, rather than colour and texture
information, systems become invariant to lighting conditions. Secondly, the ability to
rotate a facial structure in three-dimensional space, allowing for compensation of
variations in pose, aids those methods requiring alignment prior to recognition. Thirdly,
the additional depth information in the facial surface structure, not available from twodimensional
images, provides supplementary cues for recognition.
The Fishersurface Method
In this section we provide details of the fishersurface method of face recognition. We
apply PCA and LDA (linear discriminant analysis) to surface representations of 3D face
models, producing a subspace projection matrix, as with Belhumier et al’s fisherface
approach [12], taking advantage of ‘within-class’ information, minimising variation
between multiple face models of the same person, yet maximising class separation. To
accomplish this we use a training set containing several examples of each subject,
describing facial structure variance (due to influences such as facial expression), from
one model to another.
The Test Database
Until recently, little three-dimensional face data has been publicly available for research
and nothing towards the magnitude required for development and testing of threedimensional
face recognition systems. In these investigations we use a new database of
3D face models, recently made available by the University of York, as part of an
ongoing project to provide a publicly available 3D Face Database [13]. Face models are
generated in sub-second processing time from a single shot with a 3D camera, using a
stereo vision technique enhanced by light projection.
Surface Space Analysis
In this section we analyse the surface spaces produced when various facial surface
representations are used with the fishersurface method. We begin by testing the variety
of fishersurface systems introduced by Heseltine et al [1] on test set A, showing the
range of error rates produced when using various surface representations (Figure 3).
Continuing this line of research we persist with the same surface representations,
referring the reader to previous work [1, 9] for implementation details, while in this
paper we focus on the effect and methodologies of combining multiple systems, rather
than the surface representations themselves.