Image Processing Reference
In-Depth Information
1
Where
A
A( i , j )
.
2
(N
1)
1i,j N 1
Let
A
it is
N
a-dimensional vector of signs . Accepting total number of vectors for
training of neural network as
L
{,
and their average according:
,...,
}
12
L
L
1
L
,
i
i1
*
i i
,
i1,2,...L.
The covariace matrix will be:
*
*
*
*
*
*
T
C
[
,
,...,
][
,
,...,
]
/ ( L
.
1)
12
L
12
L
Let eigenvalues and eigenvectors C - {
λ1, λ2,
λL
} and {
ξ1
,
ξ2
, …
ξL
},
{
...
}
1
2
L
1
L
accordingly.
Eigenvectors corresponding
M
greatest eigenvalues, form a vector of features
V
= [
λ1, λ2,
*
as a result
λM
]
T
. The experiments led by authors, shown that
M
15
is enough.
*
transforms to
with dimensionality reduction. Recognition of the image belonging to
the specific camera was carried out by trained neural network of direct propagation with 15
input neurons, 50 neurons in the hidden layer (with tangential activation function) and one
output neuron (sigmoidal activation function). If we denote a set of color interpolation
algorithms D:
V
i
i
*
DD{
where is the empty set corresponding initial
I(
.
Identification by color interpolation consists in defining conversion
*
}
d
which with the
greatest probability has been fulfilled over
I(
, i.e. the purpose is to reference available
I(
to one of classes
D
of the learning images set nearest to
I(
, in space of conversion
characteristics of debayerization. Thus, to each class of images one neural network should
be set in correspondence. To select total number of neural networks the following conditions
according to authors is necessary to consider. For the different
d
it is necessary to use
*
different neural networs (
) considering essential difference of
debayerization operators, applied to the channel of "green" and channels "red"/"blue"
should use different neural networks for each color component. By authors of a method the
best result were shown when three networks was used, one for each channel. Thus the total
of neural networks makes
d,d
D,d
d
12
1
2
*
DD1
for each channel and
3( D 1
totally [12]. The given
method does not depend on color channels used for identification, on each channel the
independent decision which is pseudo-independent, as channels are mutually correlated as
shown in [13-14]. Accuracy of identification has been checked by authors on learning and
test samplings on 100 images [13]. Accuracy of recognition of 7 algorithms of the
interpolation was 100 % (errors of the first and second type are equal to zero). Accuracy of
classification by offered methods oт real photocameras made 95-100 % depending on a
