Fusion of Visual and Thermal Face Recognition Techniques: A ...

A number of earlier face recognition algorithms are based on feature-based methods
[9][10][11] that detect a set of geometrical features on the face such as the eyes,
eyebrows, nose, and mouth. Properties and relations such as areas, distances, and angles
between the feature points are used as descriptors for face recognition. Typically, 35-45
feature points per face were generated. The performance of face recognition based on
geometrical features depends on the accuracy of the feature location algorithm. However,
there are no universal answers to the problem of how many points give the best
performance, what the important features are, and how to extract them automatically.
Appearance-based face recognition algorithms proceed by projecting an image into
the subspace and finding the closest point. Linear discriminant analysis (LDA) and
principal component analysis (PCA) have been two approaches widely used for
dimensionality reduction and feature extraction [12]. Several leading commercial face
recognition products use face representation methods based on the PCA or Karhunen-
Loeve (KL) expansion techniques, such as Eigenface [13] and local feature analysis
(LFA) [14][15][16]. Multispace KL is introduced as a new approach to unsupervised
dimensionality reduction for pattern representation and face recognition, which
outperform KL when the data distribution is far from a multidimensional Gaussian [17].
Discriminant analysis based on Fisher’s linear discriminant function [18][19] has been
widely employed in face recognition. LDA determines a set of optimal discriminant basis
vectors so that the ratio of the between- and within-class scatters is maximized. The LDA
could be operated either on the raw face image to extract the Fisherface [20][21] or on the
eigenface to obtain the discriminant eigenfeatures [22][23].
7