F-LOCKER: An Android Face Recognition Applocker Using Local Binary Pattern Histogram Algorithm

Abstract— Smartphone is one of the important assets of
today’s generation it makes people more responsive,
productive and effective in work and in personal dealings.
Remarkably it is used as the primary repository of
individual confidential files because of its portability and
reliability which provide a scheme to smartphone
companies to embed security features and users install
security application freely available in the market. In most
various studies, facial recognition marked the highest
security features. So, this study aims to develop a facial
recognition application specifically for an android phone
using a local binary histogram algorithm and V-Model to
process the development of the application. Furthermore,
this application is tested and evaluated by the experts with
a score of 4.59 weighted mean “Excellent” based on its
functionality, reliability, usability, efficiency and
portability.
Index Terms— face Recognition, applocker, identity
theft, security on smartphones.
I. INTRODUCTION
ecurity is about confidentiality, availability, and integrity of
data [24] and this must be protected with reliable solutions
since information are in placed in various platform offers data
keeping capability. Majority of the users nowadays preferred
to keep data using their smartphone devices. Smartphone is
one the important assets in the 21st century [44] and this lead
the fast development of smartphone open platform [5] [47]
design with multi-layered security[36].With the evolution of
technology and research conducted to strengthen the existing
solutions in security it produces innovative applications [15]
[35] [21] . Notably there are various security applications
embedded and integrated to smartphone devices such as
patterns, pin, password and face recognition however among
these security solutions, face recognition ranked the best
according to recent researchers [14] [21] as this is one of the
emerging field of research. In fact there are security
applications freely available in the market [17]. Moreover,
security application should strong security architectures and
meticulous security programs [20] and this must be reliable
and accurate [23] to ensure that vital information is secured
[34] [2] and protect individual safety and individual property
[36]. As reported smartphones face an array of threats that
take advantage of numerous vulnerabilities [19]. These
vulnerabilities can be the result of inadequate technical
controls, but they can also result from the poor security
solutions [27]. The current research on face recognition
applied different techniques and algorithms to achieve
recognition rate which address complex variation to make the
recognition reliable and accurate and this can be used in
various application [8] like protection in the mobile phone
which is used to unlock the devices [39]. Moreover face
recognition features application reduces the risk of forgetting
passwords and to fasten authentication [34]. Also, it provides
a strong mechanism to authenticate unique features of the
authorized users [25], [18], [51]. In this study a Local Binary
Pattern algorithm is apply for face recognition for its
implicitly and efficiency [32], [42], [45].
A. Project Context
An estimated number of 3 billion smartphone users are
expected this 2016 with at least 72% of it are Android users
[4] worldwide. In Asia, as one of the leading continent in
developing smartphones, like in Japan [50], South Korea [23],
Singapore [39] and China [52], it also has the most number of
Android users compared to the Americas, Europe and
Australia [31]. In the Philippines, it is considered as the fastest
growing smartphone country with at least 35% of its
population using smartphones and 58% of those are Android
users [10] With these numbers, a greater number of users
experience personal information and sensitive data leaks. 78%
of smartphone users had experienced personal identity
information leaks, including their name, personal files,
pictures and classified videos [43]. The security of mobile
phones is then raised to the masses. There are different causes
affecting the security of mobile phones. Mobile phones often
lack passwords to authenticate users and control access to data
stored on the devices increasing its risk that stolen or lost
phones' information could be accessed by unauthorized users
who could view sensitive information and misuse mobile
devices [20]. In other cases, the authentication lacks due to an
easy pattern combination or pin number [24] which can be
guessed, forgotten, written down and stolen, or eavesdropped
[42]. Lastly, to avoid tracking, the phone’s location tracking is
turned off by most users [50] hindering its capabilities in
added security in case stolen or misplaced [12].Existing
security applocks have easy set of authentications, resulting to
a same factor of security the Android itself offers [17]. In
contrary, other applocks have a difficult set of authentications
giving a long time for users to open their phones and
applications [50]. Furthermore, most of the applocks available
in the market can be easily removed or uninstalled [11]. The
poor security authentication of most applocks can still harm
the protection aimed by the user upon download [20]. The face
of a human being conveys a lot of information about
someone’s identity [48]. To make use of its distinctiveness,
facial recognition is developed [47]. As every person is unique
upon others, facial recognition offers the most secured
F-LOCKER: AN ANDROID FACE RECOGNITION APPLOCKER
USING LOCAL BINARY PATTERN HISTOGRAM ALGORITHM
ALA Ramos, MAM Anasao, DB Mercado, JA Villanueva, CJA Ramos, AAT Lara, CNA Margelino
Institute of Computer Studies, Saint Michael’s College of Laguna, Philippines
S
International Journal of Computer Science and Information Security (IJCSIS),
Vol. 16, No. 2, February 2018
129 https://sites.google.com/site/ijcsis/
ISSN 1947-5500

protection and authentication for smartphones [46]. Face
recognition is an interesting and challenging problem and
impacts important applications in many areas such as
identification for law enforcement, authentication for security
system access, and personal identification [28]. Compared to
passwords, it provides distinctive print to gain access [18]. It
does not only make stealing of passwords nearly impossible
but also increases the user-friendliness in human-computer
interaction [2].
B. Statement of the Problem
General Problem
The researchers found out that there is no existing high
security mobile application other than finger print, which is
only available in few model of android smartphones, that is
reliable and accurate security tools for securing important data
and application in mobile devices.
Specific Problems
 The Android smartphone’s PIN, Pattern, and Password can
be easily determined.
The researchers conducted an interview if they encounter
password theft, according to them most of their experience
happens when some relatives and friends see through their
password. To further investigate, the researchers, conducted a
survey to 340 respondents asking the users about using
security applications on how often you change your security
application using password is Six (6, 1.76%) changes
regularly or every day; eighty-four (84, 24.71%) changes
every week; one-hundred forty-five (145, 42.65%) changes
every month; thirty-six (36, 10.59%) changes every year; and
thirty-nine (39, 11.47%) rarely change their password. The
majority of respondents changed their password (PIN, Pattern,
and Password) monthly which means that they are not
satisfied to their security so they need to change often.
 Lack of higher security
to protect applications for almost of lower to highest model
of Android smartphones from unauthorized users.
Most of the people nowadays have important files in their
devices. And based on result in survey conducted on which
security application the android users’ using is eighty-two (82
or 24.12%) used Smart Lock; one-hundred ten (110 or
32.35%) uses CM Lock; one-hundred twenty-four (124 or
36.47%) uses Applocker; fourteen (14 or 4.12%) uses Finger
security; one (1 or 0.29%) uses Privacy Knight; three (3 or
2.65%) do not use other application. With these results,
majority used Applocker which means that the researchers
need to put more attention in securing applications in android
smartphones for lack of security for apps in any other security
apps.
C. Research Objectives
General Objective
To develop an android application that will utilize the existing
security tools, facial recognition, for the selected application
in android smartphones.
Specific Objectives
 To develop an application that applies Face Recognition
Security using Local Binary Pattern Algorithm.
The system will use a higher method of security than the
traditional method such as, pattern, PIN, password, which is
the face recognition.
First the user will need to install the APK of the system, it
must be opened to set the security. Second, the system will ask
to “Activate Device Administrator”, click “Activate”. Then, it
will proceed in detecting face to save it as a security.
Afterwards, it will ask for a PIN to register as a backup or
alternative security to act as a secondary for the times that the
face recognition is not applicable with the environment.
 To develop a system that will secure all application using
the Start Service and Block method
The system will give security to those applications which
the user’s selected. It has the capability to have a “Start
Service” and “Block” the individual applications from
opening, both built-in applications and downloaded
applications. After setting the security, the system now is
ready to use. The only thing that users need to do is to select
all the application-installed listed in the system to give a
security and then click “save”, and it’s done. All the
application selected will be given a face recognition security
before it opens. If the face doesn’t match, within 3 attempts,
on the database, it will be forced to close.
D. Scope and Limitation
Scope
The study focused on face recognition app locker for android
smartphones. The application includes the following features:
Security Module - This module allows the user to use the
facial recognition as password before the selected applications
to be opened. There will be another security method the PIN
as alternative if the facial recognition is not applicable in case
black out mode.
Application Choice Module - This module allows the user to
choose applications in which the application would give
security features.
Image module - This module, through the use of Open CV, it
will convert image to string/array.
Face Recognition Module - This module allows the user to set
a face as primary security, furthermore this module allows the
user to scan and compare the face detected before the selected
applications to be opened.
Pin Module - This module allows the user to set 4 to 6
characters as secondary security that can be used in case that
face recognition isn’t applicable because of the environment.
Limitations
 It is unable to recognize subject wearing sunglasses or
when any object portrait as a barrier to the special facial
features.
 The system would only capture around less than 2 meters
distance.
 When a face is train in the recognition software, usually
multiple angles are used (profile, frontal and 45-degree
are common). Anything less than a frontal view affects
the algorithm’s capability to generate a template for the
face.
ISSN 1947-5500

E. Significance of the Study
The results of this study will be beneficial to the following:
Users - The study will reduce the identity theft and intrusion
of privacy in android smartphones.
Application Developers - This study will serve as a reference
for application developers in terms of security and protection
for android applications.
Researchers - The study will adapt those technical skills
they’ve learned from their Computer Science Course.
Future Researchers - The study can be a basis for future
researchers.
II. METHODOLOGY
The researchers applied the concept of V-model to ensure the
accuracy of every stage in the development of the application
process.
Fig. 1. Verification Model
System Requirements Specifications
In this phase, the researchers identified the requirements
of the proposed application
Investigate the present-day conditions
The researchers conducted a survey to three-hundred
forty (340) Android smartphone users. The survey
questionnaire will serve as reference or basis towards the
development of the solution.
Identify the requirements
The researchers identified the requirements through
identified the hardware and software requirements, the
process and techniques to be applied for the
accomplishment of the study.
High Level Design
In this phase, the researchers arranged the course of the
proposed project, the user interface design, and the
database design.
Outline of the System Design
The researchers laid down the concept of the process,
techniques and strategies with estimated required time of
completion. The concepts are interpreted through a
diagram to visually see the flow of the application.
Low Level Design
In this phase, the researchers applied the technical aspects
of the application, the algorithm which detects face
recognition, the database design, and the system
architecture
Implementation
In this phase, the researchers conducted an
implementation phase where the application is installed
and be tested by the experts. All issues relative to
functionality of the application is immediately be solved
and identified.
Coding
In this phase, the researchers performed the coding
aspect of the application based on the outline of the
requirements and classes of modules are reviewed
carefully.
Testing
In this phase, the researchers conducted a series of test to
make a walkthrough analysis of every phases of the
module to ensure acceptability and suitability.
Furthermore the application is evaluated based on ISO
characteristics.
A. Algorithm
The researchers used Local Binary Patterns Algorithm to
analyze the face images in terms of shape and texture. The
face area is divided into small regionals then it will be
extracted and concatenated into a single vector though a
binary pattern through pixels to efficiently measure the
similarities between images. LBPH consist of binary patterns
through pixels.
III. RESULTS AND DISCUSSION
The researchers specified the requirements needed:
TABLE I
SYSTEM REQUIREMENTS
ANDROID OPERATING SYSTEM VERSION
Android Operating System
Version
Minimum: Lollipop
Maximum: Nougat
Android database SQLite
Android Programming
Software
Android Studio
Fig. 2. Local Binary Patterns Algorithm
Fig. 2. The algorithm consists of binary patterns that describe
the surroundings of pixels in the regions. The obtained features
from the regions are concatenated into a single feature histogram,
which forms a representation of the image. Images can then be
compared by measuring the similarity (distance) between their
histograms. Because of the way the texture and shape of images
is described, the method seems to be quite robust against face
images with different facial expressions, different lightening
conditions, image rotation and aging of persons.
ISSN 1947-5500

The minimum version requirement of F-Locker is lollipop, for
this is the lowest version only that is capable for face
recognition, while the maximum version requirement is
Nougat.
Fig. 3. Conceptual Framework
Fig. 3 shows the conceptual framework of the F-Locker. The
OpenCv is utilized to influence the face acknowledgement
used to capture the image. It will be saved as, from image to
string/array. The detection of the face in pixels will depend on
how much was the face area captured. This face image stored
in database will serve as training data set. It will be used as a
base-comparing-data for the new face image detected, to
analyze and compare. The locked application/s will be
unlocked if and only if it matches the stored face image.
Fig. 4. System Architecture
Fig. 4. shows the system architecture of the application. The
user of the application will train its face to save it as password
for his chosen application that he wants to lock. Each nodal
point that the system gets in his face will be the guide for the
apps to know if it is the user or not. Every user that trains their
face will be saved to the database (SQLite) of the application.
The system will be limited from lollipop to nougat version.
The F-Locker Application Interface
Figure 5: Face Detection
Fig. 5 shows that the application detects the face image
applying the Local Binary Pattern Histogram algorithm. Once
the face image is detected it will be processed through
comparing the face image versus the training data sets stored
in the application. Once matched, the applications will
automatically open.
Fig. 6. PIN Password
Fig. 6. shows the used of PIN password as alternative security
application once experiencing blackout and the surrounding
environment is dark.
Fig. 7. Applications
Fig. 7 shows all the application installed in a phone. These
applications can be locked by selecting the key icon beside.
Fig. 8. Face Verification
Fig. 8 shows a notification that the detected face cannot access
the application which means that the face image does not
matched the training data sets.
ISSN 1947-5500

TABLE II
SOFTWARE EVALUATION SURVEY RESULTS
All Characteristics Mean Verbal Interpretation
Functionality 4.63 Very Satisfactory
Reliability 4.64 Very Satisfactory
Usability 4.52 Very Satisfactory
Efficiency 4.62 Very Satisfactory
Portability 4.57 Very Satisfactory
Total Weighted Mean 4.60 Very Satisfactory
The researchers submitted the application for software
evaluation using the ISO 9126 evaluated by the experts. Based
on result the application marked an average weighted mean of
4.60WM, “Very Satisfactory” which means that the majority
of the application meet the specified requirements:
Functionality marked a weighted mean of 4.63WM, “Very
Satisfactory”, Reliability marked a weighted mean of
4.64WM, “Very Satisfactory”, Usability weighted mean of
4.52 WM, “Very Satisfactory”, Efficiency weighted mean of
4.62WM, “Very Satisfactory, and Portability with a weighted
mean of 4.57WM, “Very Satisfactory”.
IV. CONCLUSION
The researchers have concluded that the developed system
verify enough convenience, suitability, and ease for the user to
have higher security in their android phones.
The application offers reliability to reduce identity theft and
data intrusion for each application installed in their respective
android smartphone.
V. RECOMMENDATION
The researchers recommended the following features to
improve the application.
 Consider resolving complexity issue like wearing hats,
different kinds of eye glasses, and environment issues like
lightning conditions.
 Used an algorithm to detect all angles of the face.
 Employed more security features.
ACKNOWLEDGMENT
The researchers would like to express our gratitude to the
people who help us this study possible, Mr. Adrian Evanculla
and Ms. Karla Mirazol P. Maranan for sharing their technical
expertise to make the study be realized, Mr. Michael Jessie
Theodore for testing and checking the capability of the
application.
REFERENCES
[1] AddictiveTips (2017). Prevent Intrusion of Private
Application. Available:
http://www.addictivetips.com/android/best-free-android-
tools-to-lock-password-protect-apps/
[2] Adkins, A. (2015)” Implicit Authentication Based on
Facial Recognition on Android Smartphones.”
Cambridge, United Kingdom: Cambridge University
Press.
[3] Aludjo, A (2015). Why mobile security is more important
than ever before.Available:
http://www.welivesecurity.com/2015/11/06/mobile-
security-important-ever/
[4] Ambajan, S. (2016). Worldwide Active Android
Smartphone Users To Reach More Than 2 Billion By
2016. Daze Information website
[5] Amuli G. (2017). App Lock: The Security System for
Unprotected Mobile Apps Available:
https://securingtomorrow.mcafee.com/consumer/mobile-
security/app-lock-the-security-system-for-unprotected-
mobile-apps/
[6] Apolline F. (2017) Best App Lockers For Android.
Available: http://beebom.com/best-app-lockers-for-
android/
[7] Aria, U. (2017) “Introduction to Facial Recognition:
Local Binary Pattern Algorithm.” Glasgow, UK:
University of Strathclyde
[8] Asija, S. (2016).“A Local Binary Pattern Algorithm for
Face Recognition.” Bengaluru, India: Indian Institute of
Science
[9] Baay R. (2014) Android Security (2014). Available:
www.androidauthority.com/android-security-patches-
june-777079/
[10]Berry, R., Najmul, T. &Tanz, J.O. (2011) “Facial
Recognition using Local Binary Patterns (LBP)
Algorithm.” Singapore: Nanyang Technological
University
[11]Bianchi, A. (2011). “The Phone Lock: Shoulder-surfing
Resistant PIN Entry Methods for Mobile Devices.”
Queensland, Australia: Eider Press
[12]Bruggen, D.V. (2012) “Modifying Smartphone User
Locking Behavior.” New York, USA: Macmillan
Publishing Company.
[13]Bump, S. (2015) “Local Binary Pattern Algorithm.” Bath,
UK: University of Bath.
[14]Crysta M. (2017) A Secure Screen Lock System for
Android Smart Phones using Accelerometer Sensor
Available:
http://www.ijste.org/articles/IJSTEV1I10060.pdf
[15]De Luca, A. (2015) “Implicit Authentication Based on
Touch Screen and Facial Patterns.” New York City, USA:
HarperCollins Publishers.
[16]Ellani D. (2017) Identifying Strengths and Weaknesses of
a Security Program . Available:
https://www.optiv.com/resources/library/identifying-
strengths-and-weaknesses-of-a-security-
program?page=1&searchQuery=&itemsPerPage=0&categ
or y
[17]Findling, R. (2015) “Lack of Security in Smartphones.”
Kota, India: University of Kota.
ISSN 1947-5500

[18]Harbach, M. (2015). The Anatomy of Smartphone
Unlocking. New York City, USA: Bloomsbur.
[19]Iraldy K. Implementing Speech Recognition Algorithm
(2016). Available:
http://www.ti.com/lit/an/spra178/spra178.pdf
[20]Irish Malia C. (2017). How To Bypass Android Phone
Lock. Available: http://trendblog.net/how-to-bypass-
android-phone-lock-screen-pattern-pin-password/
[21]Jae, K.P (2015). Studying Security Weaknesses of
Android System. Available:
http://www.sersc.org/journals/IJSIA/vol9_no3_2015/2.pd
f
[22]Kaur, A. &Taqdir, S.S. (2015). A Face Recognition
Technique using Local Binary Pattern Method.
Bengaluru, Karnataka, India: DnI Institute
[23]KeyLemon (2017). Facial Recognition. Available:
https://www.keylemon.com/
[24]Keylemon, J. (2014). Multi-Factor Authentication.
Available: https://www.keylemon.com/
[25]Kim, S.H. (2011). A Shoulder-surfing Resistant Password
Security Feature for Mobile Environments using Facial
and Fingerprint Pattern. Washington, D.C., USA:
American University.
[26]Lengge H. (2017) How To Protect Your Privacy Using
Android Available:
http://www.androidauthority.com/android-privacy-guide-
624787/
[27]Lopez, S.L. (2013) “Local Binary Patterns applied to Face
Detection and Recognition.” Rio de Janeiro, Brazil: Brazil
de Univerzidad.
[28]Lucero A (2017). You Need to Know About Encrypting
Available: http://www.howtogeek.com/141953/how-to-
encrypt-your-android-phone-and-why-you-might-want-to/
[29]Marc B. (2017). Best and Common Top 3 Algorithm
Used in Security Available: (Programmer’s Developers’
Page)https://www.facebook.com/groups/ProgramersDevel
opers/
[30]Marielia Q (2017). Implementing Hash Function Day
(2017). Available:
https://en.wikipedia.org/wiki/Hash_function,
[31]Marvs Ria Wo (2017). Why is Mobile Phone Security
Important? Available:
http://www.parallels.com/blogs/ras/why-mobile-phone-
security-important/
[32]Midda S. (2017) Android Power Management: Current
and Future Trends Available:
http://www.eurecom.fr/en/publication/3710/download/cm
-publi-3710.pdf
[33]Monteith, C. Applications of Local Binary Patterns (LBP)
ALgorithm. Toronto, Canada: Toronto State University.
(2013).
[34]Neas C. (2015). Studying Security Weaknesses of
Android System (2015). Available:
http://www.sersc.org/journals/IJSIA/vol9_no3_2015/2.pd
f
[35]Peppi M. (2017). Common Web Application Weaknesses
(2017). Available:
https://www.htbridge.com/vulnerability/common-web-
weaknesses/
[36]Protect your privacy and avoid spyware with these tips
(2016). Available:
https://blog.lookout.com/blog/2016/06/02/spyware/
[37]Radda S. (2017) How to protect your privacy on
smartphones and tablets Available:
https://www.comparitech.com/blog/vpn-privacy/how-to-
protect-your-privacy-on-smartphones-and-tablets/
[38]Rapie U. (2017). Best Security & Privacy Apps for
Smartphones & Tabletshttp Available:
https://www.makeuseof.com/tag/security-software-
smartphone-tablet/
[39]Rio, A. (2014) “Complexity Metrics and User Strength
Perceptions of the Pattern-Lock Graphical Authentication
Method.” London, UK: John Wiley & Sons.
[40]Sajon, B. (2014). Security Protection: Computer.New
Jersey, USA: Prentic Hall,
[41]Sipes, L., Jr. (2011). Top Ten Factors Contributing to
Violent Crime-Updated. Available:
http://www.crimeinamerica.net/2011/02/22/top-10-
factors-contributing-to-violent-crime/
[42]Soumya K.D. (2011). Android Power Management:
Current and Future Trends. Available:
http://www.eurecom.fr/en/publication/3710/download/cm
-publi-3710.pdf
[43]Srivastava, P. (2014). Android Application: Introduction.
NewDelhi, India: Taxmann Publications.
[44]Uellenbeck, S. (2013) Quantifying the Security Of
Graphical Passwords: The Case Of Android Unlock
Patterns. Bengaluru, India: Indian Institute of Science.
[45]VodaCom (2017). Voice Recognition. Available:
http://www.vodacom.co.za/vodacom/services/internet/voi
ce-password
[46]Wang, H.P. (2014). Number of Smartphone Users to
Quadruple in 2014. Available:
https://www.parksassociates.com/blog/article/pr-
march2014-smartphones
[47]Wang, Y. & Jade, A.R. (2014). Local Binary Patterns and
Its Application to Facial Image Analysis: A Survey.
Milton Keynes, UK: Open University
[48]Weinberg, G. (2015). How To Protect Your Privacy On
Android. Available at the DuckDuckGo website:
https://spreadprivacy.com/android-privacy-97be67d6e30b
[49]Wildes, K. (2016). Face Detection and Recognition.
Finland: University of Oulu
[50]Woodford, C (2014). Voice recognition software.
http://www.explainthatstuff.com/voicerecognition.htmlM
ohammed, J.Z.
ISSN 1947-5500

[51]Zheng, N.v (2014). “Automated Students’ Attendance
Taking in Tertiary Institution using Facial Recognition.”
Beijing, China: China International Publishing Group.
Anna Liza A. Ramos is the system analyst of the team, a
Faculty and Administrator of the Institute of Computer
Studies, a member of National Board of the Philippine Society
of Information Technology Educators, presented and
published research paper in computing in various confernces
and online publication and a recipient of a Best Paper in
International Conference.
Mark Anthony M. Anasao, is the programmer of the team, a
member of iSITE organization and officer of Junior
Information System Security Association, Philippine Chapter
freelancer programmer.
Denmark B. Mercado, is the document analyst of the team
and a member of iSITE organization
Joshua A Villanueva is the designer and artist of the team.
Christian Jay A. Ramos, is one of the researcher of the team,
a computer system services certified.
Arbenj Acedric T. Lara ,is one of the researcher of the team.
Cara Nicole A. Margelino, is one of the researcher of the
team
ISSN 1947-5500

F-LOCKER: An Android Face Recognition Applocker Using Local Binary Pattern Histogram Algorithm

More Related Content

What's hot (18)

Similar to F-LOCKER: An Android Face Recognition Applocker Using Local Binary Pattern Histogram Algorithm (20)

Recently uploaded (20)

F-LOCKER: An Android Face Recognition Applocker Using Local Binary Pattern Histogram Algorithm