The image objects of interest are represented by a set of features
extracted from the image. They form an N-dimensional space called the
feature space, with each dimension representing one of the features.
Each image object to be recognized is represented as an N-dimensional
vector
, called a pattern, or a sample,
which is a point in the feature space:
,
A set of classes
.
Any given pattern vector
is to be classified into one
of the
classes
. Classification process can be
carried out as a maximization process:
The number of features actually used in classification can be reduced
from to
by feature selection to (1) use only those features
most relevant to a specific application, and (2) reduce the computational
cost.
Feature selection may be achieved in two different ways:
Aome criterion is needed to guide the selection to decide which out of
the
features to choose, or how to find the matrix
.