The remainder of the thesis is organized as follow,
chapter 2 explain the proposed approach, chapter 3 shows the related work, chapter 4 contains
the applied experiments and the related datasets. And chapter 5 is the conclusion.
1.4 Thesis Outline
Liveness Detection is
an important research field in a biometric system. It’s become very active in
iris and fingerprint recognition systems, and it still limited in face
biometric systems. Liveness detection detects whether the person in front of
the camera is live (the real one ) or not live(spoofed one).Liveness
Detection use varies approaches according to spoofing method as spoofing can be
done using face image, face image with the ability
to show eye blinking and mouth movement, 3D mask,
video recorded of user’s face.
mode: used in negative recognition which prevents
the user to use many identities, as in this systems the identification is done
using one-to-many comparison to determine whether the user is true or it’s
Verification mode: used in positive recognition which aims to prevent
many people from using the same identity, as in this systems the verification
is done using one-to-one comparison to determine whether the user is true or
Biometrics systems use unique
features of the user these features are
anatomy and physiology ones as user face,
hand geometry, user voice, iris or fingerprint. These systems are commercially
available today and are already in use. The biometrics systems used in
identification modes, as there are 2
modes which are verification and identification modes.
This research uses non-intrusive approach, this research tries to enhance OULU approach that
presented in IJCB201 2 and it’s considered as one of the best
approaches in this competitions as it achieves
high performance in print attack dataset 3.OULU extract texture features and local features using LBP4, HOG5 and Gabor Wavelet6,But after
applying OULU approach in other databases the performance decreases, so this
research reaches to generic parameters
using SIFT7 instead of HOG5 on Replay Attack8, CASIA9 and NUAA10
Datasets and achieve better performance with the same SIFT parameters.
The intrusive approach
depends on user co-operation to detect
the life sign but In non-intrusive approach,
extracting the life sign without any user co-operation by detecting the eye
blinking of the user, extracting some
texture features of the face which differs from the real face and spoofed one.
determines if a live person is present at
the time of capture or spoofed one.Liveness Detection can be done using
hardware devices that have the ability to look beyond the surface of the skin
and can discriminate between the features of live skin and copies of those
features in a fraction of a second. But this hardware solution is very expensive
and the improvement in such solution is very hard. The better solution achieved
by using software applications, which can be Intrusive or non-intrusive.
1.1 State Of The Art
But the most common
used face recognition systems are easy to be attacked as listed in the National
Vulnerability Database of the National Institute of Standards and Technology
(NIST) in the US as mentioned in 1, one can spoof a face recognition system
by presenting a photograph, a video, a mask or a 3D model of a targeted person
in front of the camera. Also, there are a lot of other methods for an attack like using plastic surgery or make-up or using the photographs which considered as the most common sources of spoofing attacks because one can
easily download and capture facial images. Liveness detection research has a
vital role in anti-spoofing of face recognition systems and biometrics systems
at all. As it detects the live person in front of the camera or it’s spoofed
In an increasingly
digital world, protecting confidential information is becoming more difficult.
Traditional passwords and keys no longer provide enough security to ensure that
data is kept out of the hands of hackers and unauthorized individuals. This is
where biometric security can transform the technology sector. Biometric
authentication devices use unique traits or behavioral
characteristics, such as fingerprint, hand, face, eye (iris or retina), and voice recognition, to authenticate access to electronic assets.
Because biometric information is unique to each person as various biometrics
systems have been developed around unique characteristics of individuals. The
probability of 2 people sharing the same biometric data is virtually nil,
cannot be shared because a biometric property is an intrinsic property of an
individual, also it can’t be lost only in case of serious accident.