Intelligent multi-spectral IR image segmentation

We
present
a
neural
network
based
multi-­‐spectral
image
segmentation
method.
A
neural
network
is
trained
on
the
selected
features
of
both
the
objects
and
background
in
the
longwave
(LW)
Infrared
(IR)
images.
Multiple
iterations
of
training
are
performed
until
the
accuracy
of
the
segmentation
reaches
satisfactory
level.
The
segmentation
boundary
of
the
LW
image
is
used
to
segment
the
midwave
(MW)
and
shortwave
(SW)
IR
images.
A
second
neural
network
detects
the
local
discontinuities
and
refines
the
accuracy
of
the
local
boundaries.
The
neural
net
based
segmentation
method
is
compared
with
Wavelet-­‐threshold
and
Grab-­‐Cut
methods.
Test
results
have
shown
increased
accuracy
and
robustness
of
this
segmentation
scheme
for
multi-­‐spectral
IR
images.