Remote Sensing,
Journal Year:
2023,
Volume and Issue:
15(11), P. 2784 - 2784
Published: May 26, 2023
Traditional
image
fusion
techniques
generally
use
symmetrical
methods
to
extract
features
from
different
sources
of
images.
However,
these
conventional
approaches
do
not
resolve
the
information
domain
discrepancy
multiple
sources,
resulting
in
incompleteness
fusion.
To
solve
problem,
we
propose
an
asymmetric
decomposition
method.
Firstly,
abundance
discrimination
method
is
used
sort
images
into
detailed
and
coarse
categories.
Then,
are
proposed
at
scales.
Next,
strategies
adopted
for
scale
features,
including
sum
fusion,
variance-based
transformation,
integrated
energy-based
Finally,
result
obtained
through
summation,
retaining
vital
both
Eight
metrics
two
datasets
containing
registered
visible,
ISAR,
infrared
were
evaluate
performance
The
experimental
results
demonstrate
that
could
preserve
more
details
than
symmetric
one,
performed
better
objective
subjective
evaluations
compared
with
fifteen
state-of-the-art
methods.
These
findings
can
inspire
researchers
consider
a
new
framework
adapt
differences
richness
images,
promote
development
technology.
Symmetry,
Journal Year:
2024,
Volume and Issue:
16(12), P. 1705 - 1705
Published: Dec. 23, 2024
The
fusion
of
multi-polarized
petrographic
images
rock
thin
sections
involves
the
feature
information
from
microscopic
illuminated
under
both
plane-polarized
and
orthogonal-polarized
light.
During
process
section
images,
inherent
high
resolution
abundant
pose
substantial
challenges
in
terms
computational
complexity
when
dealing
with
massive
datasets.
In
engineering
applications,
to
ensure
quality
image
while
meeting
practical
requirements
for
high-speed
processing,
this
paper
proposes
a
novel
fast
Transformer.
model
leverages
soft
matching
algorithm
based
on
intuitionistic
fuzzy
sets
merge
redundant
tokens,
effectively
mitigating
negative
effects
asymmetric
dependencies
between
tokens.
newly
generated
artificial
tokens
serve
as
brokers
Query
(Q),
forming
lightweight
strategy.
Both
subjective
visual
observations
quantitative
analyses
demonstrate
that
Transformer
proposed
is
comparable
existing
methods
performance
achieving
notable
enhancement
its
inference
efficiency.
This
made
possible
by
attention
paradigm,
which
equivalent
generalized
form
linear
attention,
designed
loss
function.
has
been
experimented
multiple
datasets
different
types
exhibited
robust
generalization
capabilities.
It
provides
potential
future
research
diverse
geological
conditions
broader
application
scenarios.
Remote Sensing,
Journal Year:
2023,
Volume and Issue:
15(11), P. 2784 - 2784
Published: May 26, 2023
Traditional
image
fusion
techniques
generally
use
symmetrical
methods
to
extract
features
from
different
sources
of
images.
However,
these
conventional
approaches
do
not
resolve
the
information
domain
discrepancy
multiple
sources,
resulting
in
incompleteness
fusion.
To
solve
problem,
we
propose
an
asymmetric
decomposition
method.
Firstly,
abundance
discrimination
method
is
used
sort
images
into
detailed
and
coarse
categories.
Then,
are
proposed
at
scales.
Next,
strategies
adopted
for
scale
features,
including
sum
fusion,
variance-based
transformation,
integrated
energy-based
Finally,
result
obtained
through
summation,
retaining
vital
both
Eight
metrics
two
datasets
containing
registered
visible,
ISAR,
infrared
were
evaluate
performance
The
experimental
results
demonstrate
that
could
preserve
more
details
than
symmetric
one,
performed
better
objective
subjective
evaluations
compared
with
fifteen
state-of-the-art
methods.
These
findings
can
inspire
researchers
consider
a
new
framework
adapt
differences
richness
images,
promote
development
technology.
