Upload
others
View
3
Download
0
Embed Size (px)
Citation preview
Better restore the recto side of a document withan estimation of the verso side: Markov model
and inference with graph cuts
Christian Wolf
Laboratoire d’InfoRmatique en Image et Systèmes d’informationLIRIS UMR 5205 CNRS / Université de Lyon
INSA de Lyon, bâtiment J. Verne20, Avenue Albert Einstein - 69622 Villeurbanne cedex
http://liris.cnrs.fr
June 23rd 2008
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Plan
1 Introduction
2 The prior model
3 The observation model
4 Iterative graph cuts - the posterior probability and itsmaximization
5 Pre- and postprocessing
6 Results
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 2 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Plan
1 Introduction
2 The prior model
3 The observation model
4 Iterative graph cuts - the posterior probability and itsmaximization
5 Pre- and postprocessing
6 Results
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 3 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The problem
Blind ink bleed-through removal (scans of the verso side are notavailable).
The verso contents must be replaced by background.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 4 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Ink bleed-through removal
Problem : image segmentation. The classification decision foreach pixel is based on
the color/gray value of each pixelthe local structure of the image.
input recto labels verso labels
The framework : Bayesian estimation with two hidden Markovrandom fields (MRF)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 5 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Bayesian estimation
ESTIMATION
PRIOR KNOWLEDGE LIKELIHOOD OF THE DATAGIVEN THE HIDDEN VARIABLES
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 6 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Plan
1 Introduction
2 The prior model
3 The observation model
4 Iterative graph cuts - the posterior probability and itsmaximization
5 Pre- and postprocessing
6 Results
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 7 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
A classical hidden Markov random field
F
D
Observed
variable
Hidden
variable
Clique of the
Prior model
Clique of the
observ. model
P(f ) =1Z
exp {−U(f )/T}
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 8 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Why two hidden label fields ?
input segmentation
The prior should regularize fields which directly correspondto the natural process “creating” the contents.A correct estimation of the covered verso pixels, through thespatial interactions encoded in the MRF, helps to correctlyestimate verso pixels which are not covered by a recto pixel.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 9 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The double hidden Markov random field
F1
F2
D
Observed
variable
Hidden
variable
Clique of the
Prior model
Clique of the
observ. model
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 10 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The joint probability : dependence of recto and verso
w/o obser-vations, f 1
and f 2 areinde-pendent
with ober-vations,they aredependent
P(f 1, f 2, d)
=1Z
exp{−(U(f 1) + U(f 2) + U(f 1, f 2, d)
)/T}
=1Z1
exp{−U(f 1, f 2)/T
}·
1Z2
exp{−U(f 1, f 2, d)/T
}= P(f 1, f 2)P(d|f 1, f 2)
= P(f 1)P(f 2)P(d|f 1, f 2)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 11 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The prior of a single field : the Potts model
U(f ) =∑{s}∈C1
αfs +∑
{s,s′}∈C2
βs,s′δfs,fs′
δi,j ={
1 if i = j0 else
Discontinuity preserving
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 12 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Plan
1 Introduction
2 The prior model
3 The observation model
4 Iterative graph cuts - the posterior probability and itsmaximization
5 Pre- and postprocessing
6 Results
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 13 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The observation model (Likelihood)
The observation model characterizes the degradation processwhich is applied to the theoretical “perfect” image resulting in theobserved image.We suppose that there are two independent degradationprocesses for each side, followed by a combination of the two“virtual” observations :
D = φc(φ1(F1), φ2(F2))
The combination process φc assumes 100% opaque ink : a rectopixel f 1
s = 1 completely covers the verso pixel f 2s , whatever its
label.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 14 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
A Gaussian observation model
P(d|f 1, f 2) =∏
s
N (ds; µs,Σs)
µs =
µr if f 1
s = textµv if f 1
s = background and f 2s = text
µbg else
Σs =
Σr if f 1
s = textΣv if f 1
s = background and f 2s = text
Σbg else
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 15 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Plan
1 Introduction
2 The prior model
3 The observation model
4 Iterative graph cuts - the posterior probability and itsmaximization
5 Pre- and postprocessing
6 Results
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 16 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The posterior probability and its maximization
P(d) does notdepend on f 1, f 2
=⇒We can maxi-mize the jointprobabilityinstead ofthe posteriorprobability
P(f 1, f 2|d) = 1P(d) P(f 1, f 2)P(d|f 1, f 2)
∝ P(f 1, f 2)P(d|f 1, f 2)
U(f 1, f 2, d)
=∑{s}∈C1
α1f 1s +
∑{s,s′}∈C2
β1s,s′δf 1
s ,f 1s′
+∑{s}∈C1
α2f 2s +
∑{s,s′}∈C2
β2s,s′δf 2
s , f2s′
+∑{s}∈C1
12(ds − µs)
TΣ−1s (ds − µs)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 17 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The posterior probability and its maximization
Rewrite of the energy in terms of unary func-tions U1 and two types of binary functions U2and U′2
U(f 1, f 2, d)
=∑{s}∈C1
[α1U1(f 1
s ) + α2U1(f 2s )]
+∑
{s,s′}∈C2
[β1
s,s′U2(f 1s , f
1s′) + β2
s,s′U2(f 2s , f
2s′)]
+∑{s}∈C1
U′2(f1s , f
2s ; ds)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 18 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Minimization with minimum cut/maximum flow
[Kolmogorov et al., PAMI 2004] : a function ofbinary variables composed of unary terms andbinary terms is graph-representable, i.e. it canbe minimized with algorithms based on the cal-culation of the maximum flow in a graph, if andonly if each binary term E(x, y) is regular, i.e. itsatisfies the following equation :
E(0, 0) + E(1, 1) ≤ E(0, 1) + E(1, 0)
Depending on the observation ds of site s thismay or may not be the case for the observationmodel.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 19 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Minimization with minimum cut/maximum flow
Iterative optimization algorithm :
Fix/estimateInitialize lables, e.g. with k-meansrepeat• Fix f 1, estimate optimal f 2
• Fix f 2, estimate optimal f 1
until happy/dead/running out of patience
Sub problem can be solved exactly withminimum cut/maximum flowEquivalent to the α-expansion movealgorithm for a single MRF with adapatedinteraction potentials.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 20 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Minimization with minimum cut/maximum flow
Joint estimation of a subset of the graph GDetermine regular sites :Hs = 1⇐⇒ U′2(f
1s , f
2s , ds) is regular
Initialize lables, e.g. with k-meansrepeat• Fix f 1
s for all s and f 2s for Hs = 0, estimate
optimal f 2 for all s and f 2s for Hs = 1
• Fix f 2s for all s and f 1
s for Hs = 0, estimateoptimal f 1 for all s and f 1
s for Hs = 1
until happy/dead/running out of patience
=⇒ larger standard move !
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 21 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Minimization with minimum cut/maximum flow
Iterativealgorithm : onefield is fixed (e.g.f 1, the other fieldis estimated (e.g.f 2).
Regular sites(Hs ←− 1) arejointly estimated.
=∑{s}∈C1:Hs=0 α1U1(f 1
s )+
∑{s}∈C1:Hs=1 α1U1(f 1
s )+
∑{s}∈C1
α2U1(f 2s )
+∑{s,s′}∈C2:Hs=0∧Hs′=0 β1
s,s′U2(f 1s , f
1s′)
+∑{s,s′}∈C2:Hs=1∧Hs′=1 β1
s,s′U2(f 1s , f
1s′)
+∑{s,s′}∈C2:Hs 6=Hs′
β1s,s′U2(f 1
s , f1s′)
+∑{s,s′}∈C2
β2s,s′U2(f 2
s , f2s′)
+∑{s}∈C1:Hs=0 U′2(f
1s , f
2s ; ds)
+∑{s}∈C1:Hs=1 U′2(f
1s , f
2s ; ds)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 22 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
The cut graph
D
F2
F1
Dependency graph
F2
source(0/non− text)
sink(1/text)
F2
F1
source(0/non− text)
sink(1/text)
Cut graph α-exp move Cut graph proposed algorithm
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 23 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Plan
1 Introduction
2 The prior model
3 The observation model
4 Iterative graph cuts - the posterior probability and itsmaximization
5 Pre- and postprocessing
6 Results
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 24 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Estimation of the model parameters
Estimation of all parameters from the median filtered initialsegmentation (k-means).
Estimation of the likelihood parameters : empirical mean andvariance (covariance matrix).Estimation of the MRF parameters : least squares (Derin etal.)
Alternatives : Iterated Conditional Estimation,Expectation-Maximization, the meanfield theory etc.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 25 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Estimation of the MRF parameters
Least squares method [Derin et al., 1987]. Input data : pairs ofdifferent labels fs and f ′s with the same neighborhood Ns
θTp [N(f ′s , fNs)− N(fs, fNs)] = ln
(P(fs, fNs)P(f ′s , fNs)
)N(fs, fNs) = [ δfs,0,
δfs,1,γ(fs, fwe) + γ(fs, fea)γ(fs, fno) + γ(fs, fso)γ(fs, fne) + γ(fs, fsw)γ(fs, fnw) + γ(fs, fse) ]T
Least squares solution :
Nθp = p θp = N+p N+ = (NTN)−1NT
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 26 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Estimation of the MRF parameters
Least squares method [Derin et al., 1987]. Input data : pairs ofdifferent labels fs and f ′s with the same neighborhood Ns
θTp [N(f ′s , fNs)− N(fs, fNs)] = ln
(P(fs, fNs)P(f ′s , fNs)
)N(fs, fNs) = [ δfs,0,
δfs,1,γ(fs, fwe) + γ(fs, fea)γ(fs, fno) + γ(fs, fso)γ(fs, fne) + γ(fs, fsw)γ(fs, fnw) + γ(fs, fse) ]T
Least squares solution :
Nθp = p θp = N+p N+ = (NTN)−1NT
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 26 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Estimation of the MRF parameters
Least squares method [Derin et al., 1987]. Input data : pairs ofdifferent labels fs and f ′s with the same neighborhood Ns
θTp [N(f ′s , fNs)− N(fs, fNs)] = ln
(P(fs, fNs)P(f ′s , fNs)
)N(fs, fNs) = [ δfs,0,
δfs,1,γ(fs, fwe) + γ(fs, fea)γ(fs, fno) + γ(fs, fso)γ(fs, fne) + γ(fs, fsw)γ(fs, fnw) + γ(fs, fse) ]T
Least squares solution :
Nθp = p θp = N+p N+ = (NTN)−1NT
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 26 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Label identification
AssumptionMost space on the document page is occupied bybackgroundThe ink is 100% opaque and therefore a recto text pixelcompletely covers a verso pixel.
A B
(a) (b)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 27 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Replacement of the verso pixels
��������������������������������� ��������������������������������������
��������������������� !!!"""###$$�%%
&&&&''''(((())))**�++,,,---...///00�11
222233334444555566�77888999:::;;;<<�==
>>>>>>??????
@@@@@@AAAAAA
BBBBBBBBBBBBBBBBBBBBB
CCCCCCCCCCCCCCCCCCCCC
D D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D DD D D D
E E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E EE E E E
F F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F FF F F F F F F
G G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G GG G G G G G G
H H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H HH H H
I I II I II I II I II I II I II I II I II I II I II I II I II I II I II I II I II I II I I
J J JJ J JJ J JJ J JJ J JJ J JJ J JJ J JJ J J
K K KK K KK K KK K KK K KK K KK K KK K KK K K
L L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L LL L L
M M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M MM M M
N N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N NN N N N N N N
O O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O OO O O O O O O
P P P PP P P PP P P PP P P PP P P PP P P PP P P PP P P PP P P PP P P P
Q Q Q QQ Q Q QQ Q Q QQ Q Q QQ Q Q QQ Q Q QQ Q Q QQ Q Q QQ Q Q QQ Q Q QR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R RR R R R R R R
S S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S SS S S S S S ST T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T TT T T T T T T
U U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U UU U U U U U U
V V VV V VV V VV V VV V VV V VV V VV V VV V V
W W WW W WW W WW W WW W WW W WW W WW W WW W W
X X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X XX X X
Y Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y YY Y Y
Z Z Z ZZ Z Z ZZ Z Z ZZ Z Z ZZ Z Z ZZ Z Z ZZ Z Z ZZ Z Z ZZ Z Z ZZ Z Z Z
[ [ [ [[ [ [ [[ [ [ [[ [ [ [[ [ [ [[ [ [ [[ [ [ [[ [ [ [[ [ [ [[ [ [ [
\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \\ \ \ \ \ \ \
] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]] ] ] ] ] ] ]
^ ^ ^^ ^ ^^ ^ ^^ ^ ^^ ^ ^^ ^ ^^ ^ ^^ ^ ^^ ^ ^
_ _ __ _ __ _ __ _ __ _ __ _ __ _ __ _ __ _ _
` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `` ` `
a a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a aa a a
b b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b bb b b b b b b
c c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c cc c c c c c c
d d d dd d d dd d d dd d d dd d d dd d d dd d d dd d d dd d d dd d d d
e e e ee e e ee e e ee e e ee e e ee e e ee e e ee e e ee e e ee e e e
fffffffffffffffffffff
ggggggggggggggggggggg
h h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h hh h h h
i i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i ii i i i
j j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j jj j j j j j j
k k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k kk k k k k k k
l l ll l ll l ll l ll l ll l ll l ll l ll l l
m m mm m mm m mm m mm m mm m mm m mm m mm m m
n n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n nn n n n n n n
o o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o oo o o o o o o
p p p pp p p pp p p pp p p pp p p pp p p pp p p pp p p pp p p pp p p p
q q q qq q q qq q q qq q q qq q q qq q q qq q q qq q q qq q q qq q q qr rr r�ss
t tt t�uuv vv vww
xxyyzz{{
||}}
~ ~~ ~������
� �� ���
� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �
� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �
� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �
� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �
� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �
� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �
� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �
� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �� �
� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �
� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �� � � � � �
� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �
� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �� � � � � � � �
� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �
� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �� � � � � � � � � � � � � �
� �� �� �� �� �� �� �� �� �
� �� �� �� �� �� �� �� �� ������LEVEL 2
B
C
LEVEL 0
A
LEVEL 1
Leaves :
Ms =
1 f 1s = backgr. ∧
f 2s = backgr.
0 else
Os = ds
Parent nodes :
Ms =∑
s′∈s− Ms′
Os =
∑s′∈s− Ms′Os′
(∑
s′∈s− Ms′)
s− : children of site s
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 28 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Plan
1 Introduction
2 The prior model
3 The observation model
4 Iterative graph cuts - the posterior probability and itsmaximization
5 Pre- and postprocessing
6 Results
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 29 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Experiments
3 types of experiments :Synthetic images : recall/precision on pixel levelReal images, evaluation by humans : ranking of methodsReal images, evaluation by OCR : Levenstein cost andrecall/precison on character level
2 types of optimization :Simulated annealingBoykov and Kolmogorov’s implementation of minimumcut/maximum flow
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 30 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Experiments on synthetic images
Noise level Nr. of classes Errorσ = 10 K-Means (k=3) 0.25
Single MRF 0.03Double MRF 0.01
σ = 15 K-Means (k=3) 1.40Single MRF 0.23Double MRF 0.08
σ = 15 K-Means (k=3) 3.56Single MRF 0.73Double MRF 0.31
Inference with simulated annealing
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 31 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Experiments on real images
Input K-means
Single MRF Double MRF
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 32 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Experiments on real images
Input K-means
Single MRF Double MRF
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 33 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Experiments on real images
Input K-means
Single MRF Double MRF
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 34 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Experiments on real images
Input K-means
Single MRF Double MRF
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 35 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Experiments on real images
Method Ranked 1 Ranked 2 Ranked 3K-Means 18 10 36Single-MRF 13 39 12Double-MRF 33 15 16Total 64 64 64
Binomial-test : P-value of 0.00197. Significance level ofα = 0.025 =⇒ reject of H0.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 36 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Real images : input and k-means (graph cut)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 37 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Real images : single and double MRF (graph cut)
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 38 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Real images : Improvement of OCR results (graph cut)
103 pages, inference with graph cuts. OCR : Google Tesseract.Recall Precision Cost
No restoration 84.25 60.71 80,512K-Means (k=3) 90.19 73.26 47,611Double MRF 90.45 75.57 42,314
1 page, inference with graph cuts. OCR : Google Tesseract.Recall Precision Cost
No restoration 91.65 70.72 502Niblack 91.03 70.64 492Sauvola 91.75 76.66 349K-Means (k=3) 92.68 77.10 326Source separation RGB 80.72 54.53 911Single MRF 94.22 81.68 275Double MRF 94.43 83.27 262
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 39 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Computational complexity
1026×1557 2436×3320K-Means (k=3) 3.2 18.9Single MRF 9.1 40.6Double MRF 12.6 67.5
Inference with graph cutsExecution time in seconds (Pentium-M 1.86Mhz 1Gb RAM).
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 40 / 41
Introduction Prior model Observation model Iterative graph cuts Pre- and postprocessing Results
Conclusion and Outlook
The double MRF model is more natural and more powerfulthan the single MRF model.The double MRF model using binary labels naturally leads toan efficient graph cut implementation.The MRF methods based on classification beat the sourceseparation based methods in terms of OCR improvement.Perspectives :• Creation of a in-homogeneous “adaptive” observation model,
which increases the performance on larger images. Thismodel needs to take into account several text colors, as wellas the page bending process and other different kinds ofdegradation.• A hierarchical Markov model.• A discriminative model taking into account texture.
Christian Wolf - http://liris.cnrs.fr/christian.wolf Restore the recto by estimating the verso 41 / 41