Classified vector quantisation using principal components
Mahmoud K. Quweider, James B. Farison · Electronics Letters · 1998
The authors describe a novel classified vector quantisation technique that uses a principal component-based classifier. Each non-shade class is associated with a vector representing the largest principal component of the training vectors for that class. The technique works directly in the spatial domain without any preprocessing and achieves good perceptual quality and edge integrity at bit rates well below 1 bit/pixel with reduced coding complexity.