Internati
o
nal
Journal of Ele
c
trical
and Computer
Engineering
(IJE
CE)
Vol.
4, No. 6, Decem
ber
2014, pp. 939~
943
I
S
SN
: 208
8-8
7
0
8
9
39
Jo
urn
a
l
h
o
me
pa
ge
: h
ttp
://iaesjo
u
r
na
l.com/
o
n
lin
e/ind
e
x.ph
p
/
IJECE
Perform
a
nce An
alysi
s
of No Re
feren
ce Im
age Qual
ity B
a
s
e
d on
Human Perception
*
Subrahm
a
n
y
am.
Ch
,
**
D.
Venk
at
a R
a
o
,
***
N
.
Usha
Rani
*, ***
School of
Electronics, Vign
an’s Foundation
for Sc
ien
c
e,
Technolog
y
and
Res
earch
University
Vadlamudi, Guntur Dist, India
**
Narasar
a
opet
a
Institut
e
of
Eng
i
neeing
&
Te
chn
o
log
y
, Nar
a
sara
opeta
, Guntur
Di
st, Indi
a
Article Info
A
B
STRAC
T
Article histo
r
y:
Received Oct 1, 2014
Rev
i
sed
O
c
t 31
, 20
14
Accepted Nov 17, 2014
In this work,
a
No-Referenc
e
o
b
jec
tive
im
age
qualit
y
assessment bas
e
d o
n
NRDP
F-IQA metric
and
cla
ssif
i
cation based
metric ar
e tested
using LIVE
datab
a
se, which
consisting of G
a
ussian
white noise, Gaussian b
l
u
r
, Ray
l
eigh
fast fading
ch
an
nel, JPEG compre
ssed images, J
P
EG2000
images. We plot
the S
p
e
a
rm
an’s
Rank Order Cor
r
ela
tion Co
effic
i
ent [S
ROCC]
between
eac
h
of these features
and human
DMOS from the LI
VE-IQA datab
a
se using ou
r
proposed method to ascer
tain h
o
w well
the f
e
atures correlate
with human
judge
me
nt qua
lity
.
The
a
n
aly
s
is of the
te
sting a
n
d tra
i
ning
is done
by
SVM
model. Th
e prop
osed method sh
ows bette
r
results compared with
the earlier
methods. Finally, th
e r
e
sults
are g
e
nerated
b
y
usin
g MATLAB.
Keyword:
DM
OS
JPEG20
00
No-Refe
r
ence
SROCC
SVM
Copyright ©
201
4 Institut
e
o
f
Ad
vanced
Engin
eer
ing and S
c
i
e
nce.
All rights re
se
rve
d
.
Co
rresp
ond
i
ng
Autho
r
:
Su
bra
h
m
a
ny
am
. C
h
,
Research Sc
holar,
Scho
o
l
of
Electr
on
ics,
V
i
gn
an
’
s
Fo
und
atio
n fo
r
Scien
ce, Tech
no
log
y
an
d
Resear
ch Un
iver
sity
Vadl
am
udi
, G
unt
ur
Di
st
, I
ndi
a.
E-m
a
il
:
sub
r
a
h
m
a
ny
am
ch20
02
@
g
m
a
il
.com
1.
INTRODUCTION
In
terest in
t
h
e
measu
r
em
en
t o
f
v
i
su
al qu
ality can
b
e
d
a
ted
b
ack to
tim
e
s
wh
en in
terest in
qu
ality
assessm
ent
was p
r
i
m
aril
y
based
on
di
s
p
l
a
y
appl
i
cat
i
o
ns. B
u
t
as t
i
m
e
pro
g
r
e
ssed a
n
d s
o
di
d t
h
e
p
r
eval
a
n
ce o
f
i
m
ag
in
g
in
m
u
ltifario
u
s
app
licatio
n
s
,
‘Qu
a
lity’ g
o
t
d
e
fi
n
e
d
in
d
i
fferen
t
ways d
e
p
e
nd
ing
on
app
licatio
n
for
whi
c
h i
t
was
defi
ned
[
2
,
4,
15]
.
Im
age acqui
st
i
o
n e
ngi
neers
deal
i
n
g
wi
t
h
a
ppl
i
cat
i
ons
l
i
k
e l
a
ser
ran
g
e
scann
i
ng
fo
cu
sed
o
n
im
ag
in
g syste
m
asp
ects wh
en
th
ey gau
g
e
d
qu
ality;
prin
ter
eng
i
n
e
ers fo
cu
sed
on
to
n
e
,
co
lor assessmen
t and
fu
nd
amen
tal p
r
in
ting
attrib
u
t
es,
s
u
ch as a
r
ea a
nd l
i
n
e
qual
i
t
y
.
In c
ont
ra
st
,
m
e
di
cal
i
m
ag
in
g
research
ers related it with
t
h
e clarit
y with
wh
ic
h t
h
ey
co
ul
d
det
e
ct
m
a
l
f
unct
i
o
n
s
o
r
di
seases i
n
bo
dy
from
captured
im
ages, for exa
m
ple tu
m
ours
and ca
ncers
fr
om
X-Ray
im
ages [
5
,
8]
. H
o
weve
r,
fo
r the
sco
p
e
o
f
ou
r curren
t
work,
we are i
n
terested m
a
in
ly o
n
d
i
g
ital mu
lti
m
e
d
i
a ap
p
l
i
catio
n
s
targ
eted
for en
tertainmen
t
ap
p
lication
s
.
Ad
v
a
n
cem
en
t in
m
u
lti
med
i
a tech
no
log
i
es
hav
e
br
o
u
g
h
t
a h
o
s
t
of
devi
ces t
o
capt
u
re
, com
p
ress
,
sen
d
an
d di
spl
a
y
di
ffere
nt
ki
nds
of a
udi
ovi
sual
st
im
ul
a
t
i
ons. G
r
eat
eff
o
r
t
s have bee
n
d
e
vot
e
d
by
de
v
e
l
ope
rs
work
i
n
g
in
2D im
ag
e an
d v
i
d
e
o
tran
smissio
n
i
n
du
stry
to
gu
aran
tee end
u
s
er a satisfacto
r
y quality o
f
expe
ri
ence
, be
i
ng m
o
st
sal
i
e
nt
fo
r desi
gn a
nd
depl
oy
m
e
nt of any
m
u
l
t
i
m
e
di
a servi
ce [2
, 7, 1
4
]
.
Per
cept
u
al
opt
i
m
i
zati
on
o
f
m
u
l
t
i
m
e
di
a servi
ces
l
o
oks
pr
om
i
s
i
ng i
n
cu
rre
nt
era
o
f
b
a
n
d
wi
dt
h
f
a
m
i
ne cou
p
l
e
d
wi
t
h
in
creased
m
u
lt
i
m
ed
ia traffic so
as to
p
r
o
v
i
d
e
si
m
ilar q
u
a
lity
o
f
serv
ice to
co
n
s
u
m
er. In
o
t
h
e
r
word
s,
o
b
jectiv
e
fun
c
tion
wh
ile fin
d
i
n
g
o
p
t
i
m
u
m
co
n
f
iguratio
n
o
f
m
u
lti
m
e
d
i
a fra
m
e
work
can
in
co
rpo
r
ate Qu
ality o
f
Exp
e
rien
ce as
an
ad
d
ition
a
l t
e
rm
. A serv
ice n
e
twork
cod
e
s th
e
p
r
od
u
c
ed aud
i
ov
isu
a
l co
n
t
en
t to
t
r
ansmit i
t
ove
r c
o
m
m
uni
cat
i
on c
h
a
nnel
s
t
o
t
h
e c
o
nsu
m
er [
15]
.
Va
ri
ous
di
st
ort
i
o
ns
d
u
e t
o
c
o
m
p
ressi
on
, c
h
a
nne
l
noi
s
e
,
packet loss et
c are introduc
ed in
th
e
signal fro
m
th
is ch
ain
o
f
op
erat
io
n
s
fro
m
co
nten
t d
e
velop
m
en
t til
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
088
-87
08
IJECE Vol. 4, No. 6, D
ecem
ber 2014
:
939 – 943
94
0
t
r
ansm
i
ssi
on. These di
st
ort
i
o
ns i
n
vi
s
u
al
st
im
uli
,
when
pe
rceptible, m
a
r
the viewing experie
n
ce and henc
e
redu
ction
in
perceiv
e
d
v
i
su
al q
u
a
lity. Th
e red
u
c
ed
qu
ality o
f
d
i
storted
st
i
m
u
li can
b
e
j
u
dg
ed
b
y
con
d
u
c
ting
large-scale human
subjective
stu
d
i
es wh
ere
h
u
m
an
o
b
serv
ers are ask
e
d
to
q
u
a
n
tify qu
ality o
f
sti
m
u
l
u
s
sh
own
on a fi
xe
d sc
al
e [14
,
15]
.
Ho
we
ver
,
t
h
i
s
ki
nd
of h
u
m
a
n assessm
ent
i
s
tim
e, effor
t
and cost
ex
pen
s
i
v
e;
enge
n
d
eri
n
g
t
h
e nee
d
t
o
desi
g
n
al
go
ri
t
h
m
s
capabl
e
o
f
d
upl
i
cat
i
ng a
n
d
hen
ce el
im
i
n
at
i
ng
hum
an i
n
v
o
l
v
e
m
ent
alto
g
e
th
er. These d
e
si
g
n
e
d
o
b
j
ectiv
e
qu
ality in
d
i
ces can
th
en
b
e
u
tilized
fo
r m
u
lti
fariou
s app
licatio
ns
in
clu
d
i
n
g
bu
t
n
o
t
lim
i
t
ed
to op
ti
m
u
m
p
r
e-filterin
g
and
bit assig
n
m
en
t alg
o
rith
m
d
e
sig
n
at en
cod
e
r sid
e
;
optim
al reconstruction, e
r
ror
concealm
e
nt and post-filtering at
decode
r si
de a
n
d be
nc
hmarking
of im
age a
n
d
vi
de
o pr
ocessi
ng
sy
st
em
s.
2.
R
E
SEARC
H M
ETHOD
Th
e app
r
o
a
ch fo
r th
e NR
DPF- IQA (No
Refere
n
ce Disto
r
tion
Patch
Featu
r
e
Im
ag
e Qu
ality
Anal
y
s
i
s
)
t
h
at
we
have
devel
ope
d c
a
n
be
s
u
m
m
a
ri
zed as
fol
l
o
ws.
Gi
ven
a (
p
ossi
bl
y
di
st
ort
e
d
)
i
m
age, fi
rs
t
com
put
e l
o
cal
l
y
norm
a
l
i
zed lum
i
nance vi
a l
o
cal
m
ean subt
ract
i
on a
nd
di
v
i
si
ve no
rm
al
i
z
at
i
on. T
h
e fol
l
owi
ng
are th
e equ
a
tion
s
t
o
to app
lied to
a
g
i
v
e
n
i
n
ten
s
ity i
m
ag
e [15
]
.
:
I
i,
j
I
i,
j
1
I
i
,
j
(1
)
:
I
i,
j
I
i1
,
j
I
i
,
j
(2
)
:
I
i,
j
I
i
1
,
j
1
I
i
,
j
(3
)
:
I
i,
j
I
i1
,
j1
I
i
,
j
(4
)
:
I
i,
j
I
i
1
,
j
I
i1
,
j
I
i
,
j
1
I
i
,
j1
(5
)
:
I
i,
j
I
i,
j
I
i
1
,
j
1
I
i
,
j
1
I
i
1
,
j
(6
)
:
I
i,
j
I
i
1
,
j
1
I
i
1
,
j
1
I
i
1
,
j
1
I
i
1
,
j
1
(7
)
,
l
o
g
,
(8
)
:
J
i,
j
J
i,
j
1
J
i
,
j
(9
)
:
J
i,
j
J
i
1
,
j
J
i
,
j
(1
0)
:
J
i,
j
J
i
1
,
j
1
J
i
,
j
(1
1)
:
J
i,
j
J
i
1
,
j
1
J
i
,
j
(1
2)
:
J
i
1
,
j
J
i1
,
j
J
i
,
j
1
J
i
,
j
1
(1
3)
:
J
i,
j
J
i,
j
J
i1
,
j1
J
i
,
j
1
J
i1
,
j
(14)
:
J
i,
j
J
i1
,
j1
J
i
1
,
j
1
J
i
1
,
j
1
J
i1
,
j
1
(1
5)
The eq
uat
i
o
ns
fr
om
(1) t
o
(
1
5
)
re
pre
s
ent
t
h
e feat
u
r
es
of
t
h
e di
st
ort
i
on
pat
c
hes.
It
al
so o
b
se
rve
d
t
h
at
t
h
e
no
rm
al
i
zed l
u
m
i
nance val
u
e
s
st
ro
ngl
y
t
e
n
d
t
o
war
d
s a
unit norm
a
l
Gaus
sian c
h
aracteristic for i
m
ages.
Co
m
p
u
t
e th
e
MATLAB
prog
ram
for th
e equ
a
tio
ns fro
m
(1
) to
(15).
,
Ii,
j
μ
i,
j
σ
i,
j
C
(1
6)
μ
i,
j
,
,
,
(1
7)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
ECE
I
S
SN
:
208
8-8
7
0
8
Perfo
r
man
ce An
a
l
ysis
o
f
N
o
Referen
ce
Ima
g
e
qu
a
lity ba
sed
o
n
Human
Percep
tio
n
(
S
ub
rah
m
an
yam
.
Ch
)
94
1
,
,
,
,
μ
i,
j
(1
8)
;
,
|
|
(1
9)
/
/
(2
0)
Γ
∞
0
(2
1)
,
,
,
(2
2)
,
,
,
(2
3)
1
,
,
,
(2
4)
2
,
,
,
fo
r i
Є
{1
,2
,…,
M
} an
d j
Є
{1,
2
,…
,N}
(2
5)
Th
e
NRDPF-IQA algo
rith
m
is d
e
si
g
n
e
d
fo
r t
h
is im
ag
e qual
i
t
y
assessm
ent
pu
r
pose
.
T
h
e
M
A
TLAB
co
d
e
i
s
devel
ope
d
f
o
r
ent
i
r
e e
quat
i
o
n
s
fr
om
(1
6)
t
o
(
2
5
)
.
3.
R
E
SU
LTS AN
D ANA
LY
SIS
Wh
ile
we are u
s
ing
a pro
b
ab
ilistic fram
e
work fo
r d
i
st
o
r
tion
classifi
catio
n
wh
ere
we
u
s
e the
p
r
ob
ab
ility o
f
an
im
ag
e b
e
ing
d
i
sto
r
ted
with
a
p
a
rticu
l
ar d
i
sto
r
tion
,
bu
t
ju
st
as
a proo
f of h
o
w g
o
o
d
the
feat
ues
used i
n
t
h
e fram
e
wor
k
act
as di
st
ort
i
on i
d
e
n
t
i
f
i
e
rs
and al
s
o
w
h
i
c
h di
st
o
r
t
i
o
ns are m
i
scl
a
ssi
fi
ed wi
t
h
w
h
ich
on
es,
we ar
e r
e
por
tin
g th
e co
nfu
s
ion
m
a
tr
ix
f
o
r
f
i
rs
t
st
age cl
assi
fi
cat
i
on.
We w
o
ul
d l
i
k
e t
o
poi
nt
o
u
t
that each entry in the confusion m
a
trix is
the
m
ean of confusions
across 1000 trials.
W
e
can see
from
database t
h
at fast fadi
ng a
nd JPEG2000 a
r
e confused
wit
h
each ot
her.
Also, JP
E
G
2000 a
n
d JPEG
are also
confused s
o
m
e
tim
e
s. W
N
a
nd Blur ar
e co
m
p
arativ
ely
m
o
re robu
st in
d
e
tectio
n
and
no
t con
f
u
s
ed
u
s
u
a
lly with
ot
he
r di
st
ort
i
o
n
s
.
(a)
(b
)
(c)
(d
)
(e)
(
f)
(g
)
(h
)
(i)
(j)
(k
)
(l)
(m
)
(n
)
Figu
re
1.
Im
ages f
r
om
(a) t
o
(
g
)
an
d
(h
) t
o
(
n
) are
co
nsi
d
er
f
o
r
the testin
g
b
y
SVM
As
we c
o
m
put
ed
have c
o
rrel
a
t
i
ons
fo
r eac
h
al
go
ri
t
h
m
ove
r 1
0
0
0
t
r
ai
nt
est
t
r
i
a
l
s
, we
fi
n
d
m
ean SR
OC
C
val
u
e
and the sta
n
da
rd e
r
ror ass
o
ci
ated w
ith thes
e correlation values.
We
plot
the sam
e
across the
dataset
along
with e
r
ror ba
rs
one
standard
deviation
wi
de for each of the
evaluate
d algorith
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
088
-87
08
IJECE Vol. 4, No. 6, D
ecem
ber 2014
:
939 – 943
94
2
Tabl
e
1. M
e
di
a
n
s
p
earm
a
n ra
n
k
or
dere
d c
o
rre
l
a
t
i
on co
ef
fi
cient (s
rocc) ac
ross 1000 trai
n-test co
m
b
in
atio
n
s
o
n
the
live
i
q
a database for different
wi
ndow
sizes bo
ld ind
i
cate pr
opo
sed algo
r
ith
m
K,
L JPE
G
2000
JPE
G
W
N
Blur
FF
AL
L
4 0.
9820
0.
9803
0.
9798
0.
9605
0.
9401
0.
9489
5 0.
9663
0.
9715
0.
9762
0.
9597
0.
9315
0.
9461
6 0.
9641
0.
9642
0.
9686
0.
9497
0.
9248
0.
9419
7 0.
9548
0.
9618
0.
9618
0.
9427
0.
9231
0.
9345
8 0.
9531
0.
9512
0.
9514
0.
9329
0.
9126
0.
9258
9 0.
9418
0.
9465
0.
9501
0.
9301
0.
9103
0.
9186
Fi
gu
re
2.
Q
Q
p
l
ot
o
f
sam
p
l
e
d
a
t
a
vers
us
St
an
dar
d
N
o
rm
al
IQA
4.
CO
NCL
USI
O
N
We p
r
op
o
s
ed a
No
referen
ce
i
m
ag
e
b
a
sed q
u
a
lity
assessmen
t
m
o
d
e
l NRDPF-IQA wh
ich
p
e
rfo
r
m
s
q
u
a
lity assessmen
t
o
f
an
i
m
ag
e with
out an
y in
form
at
io
n
fro
m
d
i
sto
r
tio
n
im
ag
e. No
d
i
stortio
n
sp
ecific
feat
ure
s
s
u
ch
a
s
ri
n
g
i
n
g
bl
ur
or
bl
ocki
ng
ha
s bee
n
m
odel
e
d i
n
t
h
e
al
g
o
ri
t
h
m
i
n
speci
fi
c.
The
al
g
o
ri
t
h
m
o
n
l
y
qua
nt
i
f
i
e
s t
h
e bl
i
nd i
n
t
h
e i
m
age d
u
e t
o
pre
s
ence o
f
di
st
o
r
t
i
ons. T
h
e desi
gne
d f
r
am
ework i
s
spat
i
a
l
do
m
a
i
n
,
hum
an perce
p
t
i
on ba
sed
,
sim
p
l
e
r an
d fast
er
whi
c
h m
a
kes i
t
superi
o
r
t
o
ot
he
r n
o
refe
re
nce al
go
ri
t
h
m
s
. The
i
nde
x i
s
bee
n
sho
w
n t
o
p
e
r
f
o
rm
wel
l
acro
s
s di
f
f
ere
n
t
di
sto
r
tion
s
v
e
rifyin
g its d
i
stortion
ag
no
stic
n
a
tu
re.
An
ex
h
a
u
s
tiv
e an
alysis o
f
p
e
r
f
orman
ce is d
o
n
e
u
s
ing
LI
VE IQ
A
d
a
tab
a
se on
f
i
v
e
k
i
n
d
s of d
i
sto
r
ti
o
n
s
t
h
ro
ugh
sp
ear
m
a
n
r
a
n
k
o
r
d
e
r
e
d
co
rr
el
atio
n
co
eff
i
cent. Th
e fr
am
e
w
o
r
k
is
fo
und to
p
e
r
f
o
r
m
st
atistical
ly b
e
tt
er
th
an
ot
he
r pr
op
ose
d
n
o
refe
rence
a
l
go
ri
t
h
m
s
.
REFERE
NC
ES
[1]
A. Mittal
,
R. Soundararaja
n and
A. C. Bovik, “
Making a Complet
e
ly B
lind Image Quality Ana
l
yzer
”, IEEE Signal
processing Letters, pp. 209-212,
vol. 22
, no
. 3
,
M
a
rch 2013
.
[2]
A. K. Moorth
y
and A. C. Bovik
,
“
Blind Image
Quality Assessment: From S
cen
e
Statisti
cs to Pe
rceptual Quali
t
y
”,
IEEE Tr
ansactio
ns
Image Proces
sing, pp. 3350-3
364, vol. 20
, no
.
12, 2011
.
[3]
A. K. Moorth
y
and A. C
.
Bov
i
k, “
A Two-step
Framework for
Constr
ucting Blind Image Quality Ind
i
ce
”
,
IEEE
Signal Processing Letters
, pp
. 58
7-599, vol. 17
, n
o
. 5
,
May
2010.
[4]
M. A. Saad, A.
C. Bovik and C.
Charrier
, “
Mode
l-Based Bl
ind I
m
age Quality As
sessment: A natural scene statis
tic
s
approach
in the DCT
domain
”, I
EEE Trans
action
s
Image Processi
ng, pp
. 3339-33
52, vol. 21
, no
. 8
,
2012
.
[5]
M. A. Saad
, A. C. Bovik
and
C. Charrier, “
A DCT Statistics-
Based Blind Im
age Quality Ind
e
x
”,
IEE
E
Si
gnal
Processing Letters, pp. 583-586,
vol. 17
, no
. 6
,
Ju
ne 2010.
[6]
H. R. Sheikh, A. C. Bovik, and
L.
K. Corm
ack,
“
N
o-Reference
Qualit
y As
s
e
s
s
m
ent Us
ing Natur
a
l S
cene S
t
atis
t
i
c
s
:
JPEG2000”,
IEEE Transactions
on Image
Proces
sing
, vol
. 14
, no
. 12, Decem
ber
2
005.
[7]
A. Mittal
,
G. S. Muralidhar
,
J. G
hosh and A. C.
Bovik, “
B
lind i
m
a
ge qua
lit
y as
sessm
ent without hum
an Trainin
g
using latent quality
f
actors”,
IEEE Signa
l Proces
sing Letters"
, pp
75-
78, Vol 19, n
o
2, February 20
12.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
ECE
I
S
SN
:
208
8-8
7
0
8
Perfo
r
man
ce An
a
l
ysis
o
f
N
o
Referen
ce
Ima
g
e
qu
a
lity ba
sed
o
n
Human
Percep
tio
n
(
S
ub
rah
m
an
yam
.
Ch
)
94
3
[8]
Ehsan Ollah Shey
b
a
ni
,
“
A
n
Algorithm
for Real-
T
im
e Blin
d Im
ag
e Quality
Comparison and Assessment”,
International Jo
urnal of
Electrical
and Computer Engin
eering
(
I
JECE)
,
pp. 120-1
29, vol. 2
,
no
. 1
,
Februar
y
2012
.
[9]
M.J. Chen and
A.C. Bovik, “Fast stru
ctural similarity
index
alg
o
rithm”,
Journa
l of Real-Time I
m
age Processing
,
Vol: 6
No: 4
,
Pa
ge(
s
)
:
281-287,
December
, 2011
.
[10]
Chaofeng li
, Alan Bovik and Xiaojun W
u
. “
B
lind Im
age Qu
ality Assessm
e
nt Using a
General Regression Neur
a
l
Network”,
IEEE Transactions on
Neural N
e
tworks
, 22(5), 2011. 7
93-799.
[11]
Wang Yu Ling, Yang Hu, “Machine Learning to
De
s
i
gn F
u
ll-refer
e
nce Im
age
Qualit
y s
s
e
s
s
m
en
t
Algorithm”,
TELKOMNIKA
,
pp. 3414-3421, vol. 11,
no. 6, June
2013.
[12]
R. Soundararajan and A. C.
Bovik, “RRED Indices: Redu
ced R
e
feren
ce
En
tropic Differencing
for Image Quality
Asse
ss
me
nt,
”
I
E
EE Transactions
on Image Processing
, vol. 21, n
o
. 2
,
pp
. 517-52
6, Feb
.
2012
.
[13]
A. K. Moorth
y
and A. C. Bovik,
“
B
lind Im
age Qualit
y
Assessm
e
nt: From
Scene Statistics to Percept
u
al
Qualit
y”
,
IEEE
Transactions Image Processing
,
pp. 3350-3364
,
vol. 20
, no
. 12
,
Decem
ber 2011
.
[14]
Lidong Wang, “The
Effect of
Force on
Fingerpri
nt Image Quality and Fing
erprint
Distortion”,
International Journ
a
l
of Electrical and
Comput
er
Eng
i
neer
ing (
I
JEC
E
)
,
pp
. 294-300
, v
o
l. 3
,
no
. 3
,
June 2013.
[15]
A. Mittal
,
A. K. Moorth
y
and A.
C. Bovik, “
N
o-referen
ce im
ag
e qualit
y assessm
ent in the spatial dom
ain”
,
IEE
E
Transactions on
Image Processing
, Vol: 21 No: 1
2
, Page(s
): 4695
-4708, December 2012.
BIOGRAP
HI
ES OF
AUTH
ORS
S
ubrahm
a
n
y
am
.
Ch receiv
e
d B.T
ech degre
e
in El
ectron
i
cs
and Com
m
unication En
ginee
i
ng from
Jawaharlal Nehr
u Technol
ogical University
, H
yderabad
,
Ind
i
a,
and M.Tech
degree
in Digital
Electronics
and
Communication Engine
eing fr
om JNTU, H
y
derab
d
, India.
He joined as a research schol
ar
(part time), ECE department
in Januar
y
2010
. His research
inter
e
sts includ
e signal
and im
age processing,
Computer visi
o
n
. He published
more than 20
res
earch
pap
e
rs
i
n
journa
ls
and
c
onferenc
e
s
.
Dr.Venkata Rao
published more th
an 40 technical papers in Inte
rnation
a
l and National Journals
and confer
enc
e
s
of interna
tion
a
l repu
te.
His
res
earch
int
e
res
t
s
include s
i
gn
al and
im
age
processing, wireless networks. He
carried out AICTE projects wo
rth Rs. 23 lakhs as Principal
Investigator and
Project coordinator. Dr.D
.V
enkata Rao is r
ecognized guid
e
under JNTU
Kakinada. Curr
ently
h
e
is
guidin
g
6 res
earch
sch
o
lars in
diff
eren
t univ
e
rsiti
es for
the
i
r Ph.D
in
the
areas of sign
al pro
cessing. I
m
age processing,
wireless networks. He gu
ided m
o
re th
an 50
UG
and PG projects.
He is Fellow Mem
b
er of Institu
t
i
on of Engine
ers (India) and m
e
m
b
er of Board
of Studies, Dep
a
rtment of
Electronics and
Inst
rumentation
En
gineer
ing, B
a
patla Eng
i
neering
coll
ege (Auto
n
o
m
ous
).
Dr. N. Usha Ran
i
published more than 25 technica
l pap
e
rs in Inter
n
ation
a
l and National Journal
s
and conferen
ces of internation
a
l repute. Her
research in
ter
e
sts include signal and im
age
processing, VLSI. He carr
i
ed out AICTE projec
ts like MODROB
S and Project co
ordinator
.
She
is recogn
ized
gu
ide und
er Vignan University
. Cu
rre
ntly
sh
e is gu
iding 5 res
earch
scholars in
the
university
for
th
eir Ph.D
in
the areas of
signal pr
ocessing.
Evaluation Warning : The document was created with Spire.PDF for Python.