Dimensionality Reduction Using Principal Component Analysis
Dimensionality Reduction Using Principal Component Analysis
Says How much the dimensions vary from the mean with
respect to each other.
Basics………………..
15
Principal Component Analysis (PCA)
• Information loss
− Dimensionality reduction implies •information loss !!
− Want to preserve as much information as possible, that is:
19
Face Detection
Samples at different
orientations,illuminations, different
expressions
Face Recognition using PCA
• Acquire an initial set of face images(training
set)
• Calculate the eigenfaces from the training
set,keeping only M images corresponding to
highest eigen values.These M images define
the face space.
Recognition
27
Limitations of PCA
• PCA is a linear method. It fails as the largest
variance is not along a single vector, but along a
non-linear path.
• Static Traditional PCA assumes that the
monitored process is static. Many industrial
processes do not display a stationary behavior
because the operational conditions change
• When PCA is used for clustering, its main
limitation is that it does not account for class
separability since it makes no use of the class
label of the feature vector.
Thank You