Many modern face verification algorithms use a small set of reference templates to save memory and computa- tional resources. However, both the reference templates and the combination of the corresponding matching scores are heuristically chosen. In this paper, we propose a well- principled approach, named sparse support faces, that can outperform state-of-the-art methods both in terms of recog- nition accuracy and number of required face templates, by jointly learning an optimal combination of matching scores and the corresponding subset of face templates. For each client, our method learns a support vector machine using the given matching algorithm as the kernel function, and de- termines a set of reference templates, that we call support faces, corresponding to its support vectors. It then dras- tically reduces the number of templates, without affecting recognition accuracy, by learning a set of virtual faces as well-principled transformations of the initial support faces. The use of a very small set of support face templates makes the decisions of our approach also easily interpretable for designers and end users of the face verification system.
Kodo Millet PPT made by Ghanshyam bairwa college of Agriculture kumher bhara...
Sparse Support Faces - Battista Biggio - Int'l Conf. Biometrics, ICB 2015, Phuket, Thailand, May 19-22, 2015
1. Pa#ern
Recogni-on
and
Applica-ons
Lab
University
of
Cagliari,
Italy
Department
of
Electrical
and
Electronic
Engineering
Sparse Support Faces
Ba#sta
Biggio,
Marco
Melis,
Giorgio
Fumera,
Fabio
Roli
Dept.
Of
Electrical
and
Electronic
Engineering
University
of
Cagliari,
Italy
Phuket,
Thailand,
May
19-‐22,
2015
ICB
2015
2.
http://pralab.diee.unica.it
Template-based Face Verification
2
gc ≥ϑc
genuine
impostor
true
false
s(x,tc
i
){ }i=1
p
Matcher
s(⋅,⋅)
Fusion
rule
gc (x)xFeature
extrac-on
Verifica-on
is
based
on
how
similar
the
submi#ed
image
is
to
the
client’s
templates
Client-‐specific
one-‐class
classifica:on
mean gc (x) =
1
p
s(x,tc
i
)
i=1
p
∑
gc (x) = max
i=1,…,p
s(x,tc
i
)max
Claimed
Iden-ty
tc
1
, …, tc
p
{ }
Claimed
iden-ty’s
templates
3.
http://pralab.diee.unica.it
Cohort-based Face Verification
3
Verifica-on
is
based
on
how
similar
the
submi#ed
image
is
to
the
client’s
templates
and
on
how
different
it
is
from
the
cohorts’
templates
Client-‐specific
two-‐class
classifica:on
(one-‐vs-‐all)
gc ≥ϑc
genuine
impostor
true
false
s(x,tc
i
){ }i=1
n
Matcher
s(⋅,⋅)
Fusion
rule
gc (x)xFeature
extrac-on
tc
1
, …, tc
p
{ }
Claimed
iden-ty’s
templates
Cohorts
tc
p+1
, …, tc
n
{ }
Claimed
Iden-ty
4.
http://pralab.diee.unica.it
Cohort-based Fusion Rules
• Cohort selection is heuristically driven
– e.g., selection of the closest cohorts to the client’s templates
• Cohort-based fusion rules are also based on heuristics
– Test-normalization
[Auckenthaler et al., DSP 2000]
– Aggarwal’s max rule
[Aggarwal et al., CVPR-W 2006]
4
gc (x) =
1
σc (x)
1
p
s(x,tc
i
)
i=1
p
∑ −µc (x)
#
$
%
&
'
(
gc (x) =
max
i=1,…,p
s(x,tc
i
)
max
j=p+1,…,n
s(x,tc
j
)
5.
http://pralab.diee.unica.it
Open Issues
• Fusion rules and cohort selection are based on heuristics
– No guarantees of optimality in terms of verification error
• Our goal: to design a procedure to optimally select the
reference templates and the fusion rule
– Optimal in the sense that it minimizes verification error (FRR and FAR)
• Underlying idea: to consider face verification as a two-class
classification problem in similarity space
5
6.
http://pralab.diee.unica.it
s(x, )
s(x, )
Face Verification in Similarity Space
• The matching function maps faces onto a similarity space
– How to design an optimal decision function in this space?
6
?
7.
http://pralab.diee.unica.it
Support Face Machines (SFMs)
• We learn a two-class SVM for each client
– using the matching score as the kernel function
– genuine client y=+1, impostors y=-1
• SVM minimizes the classification error (optimal in that sense)
– FRR and FAR in our case
• The fusion rule is a linear combination of matching scores
• The templates are automatically selected for each client
– support vectors à support faces
7
gc (x) = αis(x,tc
i
)
i
∑ − αjs(x,tc
j
)
j
∑ + b
9.
http://pralab.diee.unica.it
Sparse Support Faces
• Open issue: SFMs require too many support faces
– Number of support faces scales linearly with training set size
• Our goal: to learn a much sparser combination of match scores
• by jointly optimizing the weighting coefficients and support faces:
9
hc (x) = βis(x, zc
k
)+ b
k=1
m
∑ , m << n
min
β,z
Ω β, z( )=
1
n
uk gc (xk )− hc (xk )( )
2
+ λβT
β
i=1
n
∑
10.
http://pralab.diee.unica.it
z-‐step
Sparse Support Faces
10
SFM with 12 support faces
−5 0 5
−5
0
5
−5
0
5
SSFM with 4 virtual faces
−5 0 5
−5
0
5
−5
0
5
β-‐step
Solu:on
algorithm
is
an
itera-ve
two-‐step
procedure:
If s(x,z) is not differentiable or
analytically given, gradient
can be approximated
13.
http://pralab.diee.unica.it
From Support Faces to Sparse Support Faces
• A client’s gallery of 17 support faces (and weights) reduced to 5
virtual templates by our sparse support face machine
– Dataset: BioID
– Matching algorithm: EBGM
13
4.040 2.854 −0.997 −3.525 −2.208
14.
http://pralab.diee.unica.it
Conclusions and Future Research Directions
• Sparse support face machines:
– reduce computational time and storing requirements during
verification without affecting verification accuracy
– by jointly learning an optimal combination of matching scores, and a
corresponding sparse set of virtual support faces
• No explicit feature representation is required
– Matching algorithm exploited as kernel function
– Virtual templates created exploiting approximations of its gradient
• Future work
– Fingerprint verification
– Identification setting
• Joint reduction of virtual templates for each client-specific classifier
14