ClassSpecific Feature Mixture (CSFM)
To get around the one class, one feature assumption,
CSFM assumes that each class is composed of subclasses
represented by an additive mixture PDF. We assume
that class is composed of subclasses
, that have relative probabilities of
occurrence
and individual subclass PDFs
.
The mixture PDF for is given by:

(12.5) 
where
If we assume that each subclass has a different feature
(approximate sufficient statistic) to distinguish it from
a subclass dependent reference hypothesis , we
apply (2.2) to get

(12.6) 
Note that each class PDF is represented by the same library of models.
The CSFM classifier is

(12.7) 
which may be interpreted as a
dataspecific feature classifier because
for each data sample , the factor
has a dominant effect, effectively picking one feature
to classfy the sample.
Baggenstoss
20170519