FACE RECOGNITION- EMERGING BIOMETRIC SYSTEM
Introduction
Facial recognition system is a technology which can be used to
verify or identify a person from a photograph or a video frame. There are multiple
ways of facial recognition but the most commonly used one is by comparing some
selected facial features and comparing it with those faces in the database.
Also facial recognition is preferred over any other bio metric technologies
such as iris recognition, finger print scanning, voice recognition and skin
texture recognition because of its easy deployment and non-contact process.
The software tools for facial recognition can be divided into
the following types:
2D Face Recognition
2D face Recognition has three methods. The first method exploits
an isotropic smoothing, combined Gabor features and Linear Discriminant
Analysis (LDA). The second approach is based on subject-specific face
verification via Shape-Driven Gabor Jets (SDGJ), while the third combines Scale
Invariant Feature Transform (SIFT) descriptors with graph matching.
3D Face Recognition
In 3D face recognition
3D geometry of the human face is used. 3D face recognition has the potential to
achieve better accuracy than its 2D counterpart by measuring geometry of rigid
features of the face. The 3D facial recognition helps in avoiding the
shortcomings in the 2D face recognition algorithm such as, head orientation,
make-up, different facial expressions and change in lighting.
Thermal Face
Recognition
Thermal face
recognition deals with the face recognition system that takes thermal face as
an input. Thermal human face images are produced due to the body heat patterns
of the human being. Thermal Infra –Red (IR) imagery is not affected by the
ambient lighting conditions, as the thermal IR sensors can only take in the
heat pattern emitted by the object. The range of human face and body
temperature are almost the same and uniform, it varies from 35.5°C to 37.5°C
which provides a consistent thermal signature. The thermal patterns of faces
are derived primarily from the pattern of superficial blood vessels under the
skin. The vein and tissue structure of the face is unique for each person and,
therefore, the IR images are unique as well.
Applications
· In online banking, the face
recognition system will allow only the authorized person to access the bank
account through the web services of the bank. There is a possibility for the
customer to use the ATMs, mobile application, and other banking services using
biometric identification to enhance the security during transactions.
· Real-time emotion detection is a valuable
application of face recognition in healthcare. It can be used
to detect several emotions patients exhibit during their stay in the facility
and analyze the data so as to determine how they are feeling. The results of
the analysis may help identify where the patients need more attention in case
they’re in pain or sad.
· In order to attract a wider user base amongst
the stiff competition from different applications, Social Media platforms
have adopted facial recognition capabilities to diversify their
functionalities.
· In ID Management, issuing agencies
need to prevent applicants from obtaining ID documents for a second time. Face
recognition system allow agencies to find duplicate faces in multi-million
photo databases within seconds.
· In Border Control, Facial
recognition in combination with ePassorts ensures secure and fast checking of
travel documents and biometric verification of the passport holder's identity.
The 3D facial
recognition technology is a more safe biometric system as it has a high scope
to recognize, and authenticate the
facial characteristics of individuals with better accuracy.
Controversies
With all the opportunities, there are also some controversies
associated with this technology.
· Civil rights organizations and privacy campaigners
expressed their concern that privacy is being compromised by
the use of Face recognition system. Some are scared that this system could lead
to a “total surveillance society”.
· Another controversy in association with the
face recognition system is Facebook's Deep Face, with the claims alleging that Facebook is
collecting and storing face recognition data of its users without obtaining
informed consent, in direct violation of the Biometric Information
Privacy Act.
· Also, all over the world, law enforcement
agencies have begun to use facial recognition software as an aid in the
identification of criminals. Overall accuracy rates for identifying men
(91.9%) are higher than for women (79.4%), and none of the systems accommodated
a non-binary understanding of the gender. So the controversy here is that, face
recognition is an imperfect technology in the law enforcement.
Conclusion
Growing concern towards secured transaction in healthcare,
banking, retail, and government industries are increasing the adoption of
advanced biometrics system such as face recognition system. There are companies
who are offering customized face recognition solution for specific industries.
For instance, Amazon has its own cloud-based face recognition service named
“Rekognition” for law enforcement agencies. The solution is able to recognize
as many as 100 people in a single image and can perform face match against
databases containing tens of millions of faces. Growing smart phone
implementation and increasing instances of identity threats is a boost to the
use of face recognition system in these mobile devices. The widely availability
of face recognition system on smartphone may be used as a biometric system
during various business transactions. However, misinterpretation of faces
or emotions and high initial costs causes hindrance to the use of this
technology. There are multiple controversies associated with the system.
However, with advancement of face recognition technology, these limitation may
likely to be overcome.
The identification and authentication solutions will borrow from
all the aspect of biometrics in the future. This leads to “Biometrix” or “Biometric
Mix” which is capable of guaranteeing total security for all the stakeholders. Similarly, deployment of deep learning
in facial recognition system can create a technological disruption in the future. Deep learning is a central component of the
latest-generation algorithms and holds the face detection, face tracking and
face match as well as real-time translation of conversations.