Cryptography Reference
In-Depth Information
image, respectively.
Step 1:
Generate the lookup table (LUT) by using the five substeps that
follow. An array LUT[ ] is used to map the given halftone image to
the corresponding grayscale image.
(a) For initialization, i = 1, LUT[k] = 0, where 0 k 2
16
1.
(b) Divide images double HIi
i
and GI
i
into overlapping 4 4
blocks and denote them as BH
ij
and BG
ij
. In other words,
BH
ij
and BG
ij
are the j-th halftone block of halftone im-
age HI
i
and the j-th grayscale block of grayscale image
GI
i
, respectively.
(c) Calculate index k for each halftone block BH
ij
and update
the value of the intermediate LUT[k] by using Equation
16.10. Here, BG
ij
(3; 3) is a representative pixel for each
grayscale block.
k =
P
u=1
P
v=1
2
(v1)+4(u1)
BH
ij
(u;v)
LUT[K] = LUT[K] + BG
ij
(3; 3)
;
(16.11)
(d) i = i + 1. If i n, go to Step b. Otherwise, compute and
archive the final LUT[ ]. N[k] is another array used to store
the number of halftone blocks that obtain the same index
value k.
(e) For 0 k 2
16
1, LUT[k] =
LUT[k]
N[k]
.
Step 2:
Replace the element BH
ij
(3; 3) in every block BH
ij
by LUT[k],
where k is the index value of block BH
ij
calculated in Step c. When
the replacement procedure is finished, retrieve the grayscale image
with pixel values corresponding to LUT[k].
Step 3:
After applying Step 2 to a set of n training images in succession,
a set of reconstructed grayscale images called GI
0
i
, i = 1, 2,..., n,
can be retrieved. Adopt Canny's edge detector to each reconstructed
grayscale image GI
0
i
to generate an edge map EM
i
, for i = 1, 2,..., n.
Each edge map EM
i
consists of a set of 44 blocks. Therefore, the
j-th block of the edge map EMi
i
is denoted as BE
ij
. By combining
the lookup table LUT generation procedure described in Step 1 with
Search WWH ::
Custom Search