Face Recognition System (FRS) on Cloud Computing for User Authentication

CHAPTER 1
INTRODUCTION
Information Technology has always been considered a major pain point of enterprise
organizations, from the perspectives of both cost and management. However, the information
technology industry has experienced a dramatic shift in the past decade factors such as
hardware commoditization, open-source software, virtualization, workforce globalization, and
agile IT processes have supported the development of new technology and business models.
Imagine yourself in the world where the users of the computer of todays internet world dont
have to run, install or store their application or data on their own computers, imagine the world
where every piece of information or data would reside on the Cloud (Internet).
As a metaphor for the Internet, "the cloud" is a familiar client, but when combined with
"computing", the meaning gets bigger and fuzzier. Some analysts and vendors define cloud
computing narrowly as an updated version of utility computing: basically virtual servers
available over the Internet. Others go very broad, arguing anything to consume outside the
firewall is "in the cloud", including conventional outsourcing.
Cloud computing is currently one the most hyped IT innovation Cloud computing technology is
a new concept, which provides great opportunities in many areas. Cloud computing is a
collection of computers and servers that are publically accessible via internet . Cloud computing
allows consumers and businesses to use applications without installation and access their
personal files at any computer with internet access. Cloud computing provides the variety of
internet based on demand services like software, hardware, server, infrastructure and data
storage.

Benefits of Cloud Computing

1) Increase throughput Cloud computing get more work done in less time with less people.
2) Reduce costs In cloud computing, user shares computer hardware, software and data so
theres no need to spend money on hardware or software.

Face Recognition System (FRS) on Cloud Computing for User Authentication

3) Improve accessibility In cloud computing user can access data, files anytime from anywhere
via internet.
4) Requires Less Training Cloud computing takes fewer people to do more work. So there is
requirement of minimum training of hardware, software problems to user.

National Institute of Standard and Technology (NIST) describes cloud computing with five
essential characteristics such as on-demand self-service, broad network access, rapid elasticity,
measured service, and resource pooling, three service models such as Software as a Service
(SaaS), Platform as a Service (PaaS), and Infrastructure as a Service (IaaS) and also four
deployment models such as public, private, community, and hybrid

Fig 1.1 Services By Cloud Computation

1.1 Characteristics
1) On-demand self-service Cloud provides all needed computing resources as per requirement
to user.
2) Broad network access User can access cloud services using desktop, laptop, mobile phone
etc. over the internet
3) Resource pooling Cloud provider schedules resources to the user as per their requirement.

Face Recognition System (FRS) on Cloud Computing for User Authentication

4) Rapid elasticity Cloud computing has ability to quickly allocate and de-allocate the services
as per requirement.
5) Measured service Cloud providers controlling on usage of resources.

1.2 Services
1) Software as a Service (SaaS) In the SaaS model, cloud provider delivers application
softwares like MS-OFFICE, Turbo C etc. as a service to cloud user
2) Platform as a service (PaaS) In PaaS model, cloud provider deliver a computing platform
like operating system, database, web server etc. to the cloud user.
3) Infrastructure as a Service (IaaS) Main objective of any company is to reduce time and
money. IaaS model is used to fulfill these primary objectives.

1.3 service Models

Fig 1.2 Service Models

1) Public This type of cloud model available for all users.
2) Private This type of cloud model specifically applicable only for private company.

Face Recognition System (FRS) on Cloud Computing for User Authentication

3) Community This type of cloud model is shared by several companies and supports to a
specific community.
4) Hybrid This type of cloud model is a combination of two or more clouds.
According to international data corporation (IDC), there are several issues or challenges
in cloud computing like security, availability, performance, on demand payment model may cost
more, lack of interoperability standards, bringing back in-house may be difficult, how to
integrate with in-house IT, and not enough ability to customize. According to the IDCs survey
on the cloud services, security concerns are number one issue facing cloud computing. To
remove security issues specifically to identify authorized user, we proposed a new biometric
authentication system called as face recognition system (FRS).

1.4 Authentication In Cloud

As cloud users store their information to various services across the Internet, it can be accessible
by unauthorized people. So security is the most important issue in cloud computing. To provide
security we require proper authentication technique in cloud computing. Typically, authentication
is done based on information about one or more of the following:
i. Knowledge of the subject, such as password or secret information.
ii. Possession of the user, such as smart card, passport, drivers license, etc.
iii. Biometric traits of the client, such as fingerprint, The data leakage and security attacks can be
caused by insufficient authentication Cloud services are paid services so to identify authorized
user is major concern in cloud computing. In this paper, we focus on the security issues of cloud
computing, particularly on authentication. To solve authentication problem in cloud computing,
there are

Face Recognition System (FRS) on Cloud Computing for User Authentication

1.5 Key Characteristics

Cost is greatly reduced and capital expenditure is converted to operational expenditure. This
lowers barriers to entry, as infrastructure is typically provided by a third-party and does not
need to be purchased for one-time or infrequent intensive computing tasks. Pricing on a
utility computing basis is fine-grained with usage-based options and minimal or no IT skills
are required for implementation.
Device and location independence enable users to access systems using a web browser
regardless of their location or what device they are using, e.g., PC, mobile. As infrastructure
is off-site (typically provided by a third-party) and accessed via the Internet the users can
connect from anywhere.

Multi-tenancy enables sharing of resources and costs among a large pool of users, allowing
for: (gt)
o Centralization of infrastructure in areas with lower costs (such as real estate,
electricity, etc.)
o Peak-load capacity increases (users need not engineer for highest possible loadlevels)
o Utilization and efficiency improvements for systems that are often only 10-20%
utilized.

Reliability improves through the use of multiple redundant sites, which makes it suitable for
business continuity and disaster recovery. Nonetheless, most major cloud computing services
have suffered outages and IT and business managers are able to do little when they are
affected.

Scalability via dynamic ("on-demand") provisioning of resources on a fine-grained, selfservice basis near real-time, without users having to engineer for peak loads. Performance is

Face Recognition System (FRS) on Cloud Computing for User Authentication

monitored and consistent and loosely-coupled architectures are constructed using web
services as the system interface.

Security typically improves due to centralization of data, increased security-focused

resources, etc., but raises concerns about loss of control over certain sensitive data. Security is
often as good as or better than traditional systems, in part because providers are able to devote
resources to solving security issues that many customers cannot afford. Providers typically log
accesses, but accessing the audit logs themselves can be difficult or impossible.

Sustainability comes about through improved resource utilization, more efficient systems,
and carbon neutrality. Nonetheless, computers and associated infrastructure are major
consumers of energy.

Face Recognition System (FRS) on Cloud Computing for User Authentication

CHAPTER 2
BIOMETRICS
The information age is quickly revolutionizing the way transactions are completed. Everyday
actions are increasingly being handled electronically, instead of with pencil and paper or face
to face. This growth in electronic transactions has resulted in a greater demand for fast and
accurate user identification and authentication. Access codes for buildings, banks accounts and
computer systems often use PIN's for identification and security clearences.

Face Recognition System (FRS) on Cloud Computing for User Authentication

Fig 2.1 Biometrics Types

Using the proper PIN gains access, but the user of the PIN is not verified. When
credit and ATM cards are lost or stolen, an unauthorized user can often come up with the
correct personal codes. Despite warning, many people continue to choose easily guessed PIN's
and passwords: birthdays, phone numbers and social security numbers. Recent cases of
identity theft have heightened the need for methods to prove that someone is truly who he/she
claims to be.
Face recognition technology may solve this problem since a face is undeniably
connected to its owner expect in the case of identical twins. Its nontransferable. The system can
then compare scans to records stored in a central or local database or even on a smart card.

2.1 Traditional Authentication Techniques

Face Recognition System (FRS) on Cloud Computing for User Authentication

1) Password A login and password combination is the most universally used method of
authentication but it is not secured . It is very easy to hack by tools.
2) OTP OTP is a One Time Password wherein password is provided upon request. An OTP can
prevent a password from being stolen and reused. This password is valid for a limited period of
time and can only be used once. These systems are expensive.

2.2 Biometrics Authentication Techniques

Biometrics is most widely used security system now-a-days. It is helping to overcome a lot of
drawbacks of above mentioned techniques of authentication. Biometrics can be defined as an
automated methodology to uniquely identify humans using their behavioral or physiological
characteristics . That is biometrics is used as an authentication wherein the password is human
organs or physiological characteristics. There are several biometrics techniques as stated below,
1) Voice Recognition As the name suggests voice recognition involves authentication with
respect to vocal data. Voice recognition is used to authenticate users identity based on patterns
of voice pitch and speech style. But a users voice can be easily recorded and may use by
unauthorized user. Also voice of a user may change due to sickness, so making identification is
difficult.
2) Signature Recognition Signature recognition is used to authenticate users identity based
on the traits of their unique signature. People may not always sign in a consistent manner so
verifying an authorized user is difficult.
3) Retinal Recognition Retinal recognition is for identifying people by the pattern of blood
vessels on the retina. But this technique is very intrusive and expensive.
4) Iris Recognition Iris recognition is a method of identifying people based on unique patterns
within the ring-shaped region surrounding the pupil of the eye. As like retina this technique is
also intrusive and expensive.

Face Recognition System (FRS) on Cloud Computing for User Authentication

5) Fingerprint Recognition Fingerprint recognition refers to the automated method of

verifying a match between two human fingerprints. The dryness of fingers, soiled fingers can
affect the system and it can show error.
6) Hand Geometry Recognition Hand Geometry biometrics is based on the geometric shape
of the hand. It includes the size of the palm, length and width of the fingers etc. But this
technique has some drawbacks like not ideal for children as with increasing age there hand
geometry tend to change, constant use of jewellery will result into change in hand geometry, not
valid for persons suffering from arthritis, since they are not able to put the hand on the scanner
properly.
7) Palm recognition Palm recognition is based on ridges, principal lines and wrinkles on the
surface of the palm. This technique is very expensive and not appropriate for children as there
lines of palm change once they are fully grown up.

CHAPTER 3
SYSTEM ANALYSIS
All the mentioned techniques before tend to tell us that none of it is feasible & not much useful
due to its various drawbacks. To overcome drawbacks of all these security techniques and to
provide proper security for user authentication in cloud computing, we proposed to use a
biometric technique called FACE RECOGNITION.

Face Recognition System (FRS) on Cloud Computing for User Authentication

The human face plays an important role in our social interaction. Facial recognition is
one of the preferred methods of biometrics because it is a neutral, non-intrusive, easy-to-use,
which requires minimal physical contact as compared with other biometrics systems. Face
recognition is based on both the shape and location of the eyes, eyebrows, nose, lips, and chin or
on the overall analysis of the face image that represent a face as a number of recognized
faces.Face image can be captured from a distance without touching the person being identified,
and the identification does not require interacting with the person. Face Recognition System
(FRS) enables only authorized users to access data from cloud server

Fig 3.1 Face Recognition

3.1Why We Choose Face Recognition Over Other Biometric

There are a number reasons to choose face recognition. This includes the following
1. It requires no physical interaction on behalf of the user.
2. It is accurate and allows for high enrolment and verification rates.
3. It does not require an expert to interpret the comparison result.
4. It can use your existing hardware infrastructure, existing camaras and image capture
devices will work with no problems.

Face Recognition System (FRS) on Cloud Computing for User Authentication

5. It is the only biometric that allow you to perform passive identification in a one to many
environment (eg: identifying a terrorist in a busy Airport terminal.

CHAPTER 4
ARCHITECTURE OF FACE RECOGNITION SYSTEM
Face recognition is a biometric security system. As the name suggests the face acts as a password
for the systems. Face recognition security system is shown in the figure 2. Where, we proposed
authentication scheme using face recognition system (FRS).

Face Recognition System (FRS) on Cloud Computing for User Authentication

Fig4.1 System Architecture

As the diagram explains we have login option for the user after which the verification is
conducted using face of the person. Detailed architecture is explained below

Fig 4.2 Face Recognition System (FRS)

Now let us elaborate each phase in detail and understand it.
1) Image Capture It is the step where image of the person is captured wherein his or her face
is visible. In case of 2D facial recognition, a digital camera with normal resolution is needed.
2) Face Detection Face detection involves identifying the face in the captured image. In
simple words only the face of the person is seized & all other parts of the images are eliminated
3) Alignment The face captured in the camera may not be completely perpendicular to the
camera and hence the alignment needs to be determined and compensated so that it is ready to
use of recognition process.
4) Feature Extraction Feature extraction involves a process of measuring various facial
features and creating a facial template, for the purpose of matching and identification.

4.1 Face Recognition System For User Authentication

Step I New User Registration
Whenever user wants to access cloud resources, user has to register first on to the cloud server.

Face Recognition System (FRS) on Cloud Computing for User Authentication

Fig 4.3 New User Registration steps in Cloud using FRS

Following are the steps to register on the cloud server.
1) User has to fill the registration form which is provided by cloud provider. It contains detail
information about the user.
2) User has to provide valid Email ID as a username to the face recognition system at the time of
registration.
3) Face recognition system checks the Email ID against the availability of that username.
Username should not repeat or match with existing users username.
4) After checking the availability of username, the password must be created. Face image
through web camera is stored in database as a password.
5) After providing valid username and storing face image as a password, the registration on cloud
server is completed.
Step II Registered User Login
When registered user wants to access resources on the cloud server, then registered user should
login on to the cloud server. Following are the steps to login on to the cloud server.

Face Recognition System (FRS) on Cloud Computing for User Authentication

Fig 4 . 4 Registered User Login steps in Cloud using FRS

1) User should enter valid username in his login interface which was already provided by the
user at the time of registration. And for password users face is captured by web camera.
2) Face recognition system checks the username and face image as a password provided by the
user.
3) After matching the username and face image as a password, face recognition system provides
access of cloud services to the user.
4) If username or face image does not match then face recognition system displays an error
message.

4.2 Advantages
In this proposed system, there are security advantages as stated below,
1) Non-intrusive

Face Recognition System (FRS) on Cloud Computing for User Authentication

Does not change its timing or processing characteristics. Nonintrusive testing usually involves
additional hardware that collects timing or processing information and processes that information
on another platform
2) Unique I
Independent system, biometric is an intellectual part of human and hence system remains unique.
3) Cheap Technology
Technology implementation does not requires much resources and hardware support also,it could
need hardware only in the time of face image collection. Apart from that resource utilization is
minimal. Arrives for cost effective system.
4) Fast Identification
As biometric used along with cloud computation, technology deals everything in the terms of
internet, so only need of fast computation, makes works to b faster.

4.3 Applications

Replacement of PIN,physical tokens

No need of human assistance for identification

Prison visitor systems

Border control

Voting system

Computer security

Banking using ATM

Physical access control of buildings, areas etc

CONCLUSION
The services of cloud computing is based on the sharing. Cloud computing provides variety of
services like Iaas, SaaS, and PaaS. These services are paid services, so security is a major

Face Recognition System (FRS) on Cloud Computing for User Authentication

concern to identify authorized user in cloud computing. To provide cloud services only to the
authorized user, secure authentication is necessary in cloud computing. There are so many
authentication techniques like password, OTP, Voice recognition, finger recognition, palm
recognition etc. but still it has some drawbacks like at times password techniques are not
feasible, password can be easily stolen by hacker or if user uses complex password, user may
forget that password etc. So it is a better option to use face recognition system rather than
traditional or other biometric authentication techniques. The security level of cloud provider in
terms of secure authentication is much improved by using face recognition system.

REFERENCES

Face Recognition System (FRS) on Cloud Computing for User Authentication

[1] Rajesh Piplode and Umesh Kumar Singh, An Overview and Study of Security Issues &
Challenges in Cloud Computing, International Journal of Advanced Research in Computer
Science and Software Engineering, ISSN: 2277 128X, Volume-2, Issue-9, September 2012.
[2] P. Senthil, N. Boopal and R.Vanathi, Improving the Security of Cloud Computing using
Trusted Computing Technology, International Journal of Modern Engineering Research
(IJMER), ISSN: 2249-6645, Volume-2, Issue-1, Jan-Feb 2012, pp-320-325.
[3] Ganesh V. Gujar, Shubhangi Sapkal and Mahesh V. Korade, STEP-2 User Authentication for
Cloud Computing, International Journal of Engineering and Innovative Technology (IJEIT),
ISSN: 2277-3754, Volume-2, Issue-10, April 2013.
[4] R. Kalaichelvi Chandrahasan, S Shanmuga Priya and Dr. L. Arockiam, Research Challenges
and Security Issues in Cloud Computing, International Journal of Computational Intelligence
and Information Security, Volume-3, No-3, March 2012.
[5] Nils Gruschka and Meiko Jensen, Attack Surfaces: A Taxonomy for Attacks on Cloud
Services, Proceedings of the IEEE 3rd International conference on Cloud Computing, 2010, PP276-279.
[6] Minhaz Fahim Zibran, Biometric Authentication: The Security Issues, University of
Saskatchewan, 2012. [8] S. O. Kuyoro, F. Ibikunle and O. Awodele, Cloud Computing Security
Issues and Challenges, International Journal of Computer Networks (IJCN), Volume-3, Issue-5,
2011.
[7] Maninder Singh and Sarbjeet Singh, Design and Implementation of Multi-tier
Authentication Scheme in Cloud, International Journal of Computer Science Issues (IJCSI),
ISSN: 1694-0814 Volume-9, Issue-5, No-2, Sep. 2012.