IRJET-A Survey on Face Recognition based Security System and its Applications
0 likes39 views
This document summarizes research on face recognition systems and their applications. It first defines face recognition as the process of identifying or verifying a person by analyzing facial patterns and contours. It then discusses the history of face recognition research from the 1960s to modern times. Principal component analysis and eigenfaces were important early milestones. Current applications discussed include access control, security, image database searches, and more. Finally, it outlines common face recognition methods such as holistic matching, feature-based matching, and hybrid approaches.
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 06 | June-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1664
A Survey on Face Recognition based security system and its
applications
Nijara Kalita1, L.P.Saikia 2
1 MTech Computer Science & Engg , Assam Downtown University, India
2Professor, Computer Science & Engg , Assam downtown University, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Face is our primary focus of attention and it
plays an important role in conveying identity and emotions.
We meet numbers of faces throughout our lifetime but it is
quite robust to identify despite of variation in visual
stimulus due to changing condition such as aging, beard,
glasses or changes in hairstyle. Therefore Face Recognition
system is a technology which is capable of identifying or
verifying a person from a digital image or a video frame
from a video source. Face recognition presents a challenging
problem in the process of image analysis and computer
vision. This paper describes FR, its definition, a brief history
about it, Challenges in FR, Face Recognition methods and
the various applications that are now in used in the modern
trends.
Key Words: Face Recognition, Eigenfaces, Image
processing, Face Detection, Principal Component
Analysis.
1. INTRODUCTION
Face Recognition has becoming one of the most biometrics
authentication techniques from the last few years. Mainly
the Face Recognition system has two tasks: one is
verification and the other is identification. Face
verification means 1:1 match that is verification
authenticates an individual by comparing one
specific biometric stored in the database, while
identification means comparing all the biometrics stored
in the database. Therefore face identification means 1: N
match. Machine Recognition of faces is very important
now-a-days because of the commercial and law
enforcement applications such as forensic identification,
access control, and border control. The human face plays
an important role in our social interaction, conveying
people’s identity. Using the human face as a key to
security, biometric face recognition technology has
received significant attention in the past several years due
to its potential for a wide variety of applications in both
law enforcement and non-law enforcement.
1.1 Definitions
Face Recognition is the process of capable of uniquely
identifying or verifying a person by comparing and
analyzing patterns based on the person's facial contours.
Now-a-days Face Recognition is mostly used for security
purposes, though there is increasing interest in other
areas of use. In fact, face recognition technology has
received significant to law enforcement as well as other
enterprises. Human face plays a very important role in our
social interactions and in conveying people’s identity.
Using the human face as a key to security, face recognition
technology has received a significant attention in the past
several years due to its potential for a wide variety of
applications in the research fields’ attention as it has
potential for a wide range of application related. A face
recognition system can be divided into three major steps:
a) Face Detection: Face detection is the necessary
first step in a face recognition system. The main
aim of this step is to determine whether a human
face appears in a given image.
b) Features Extraction: The main aim of this step is
to extract face component features like eyes, nose,
mouth, etc from human face image. Feature
extraction is very much important for the
initialization of processing techniques like face
tracking, facial expression recognition or face
recognition
c) Face Recognition: The main aim of face
recognition is to identify a face from the images in
the database.
1.2 History
Face detection and recognition had a huge number of
researches because of its important applications in all
fields of society as well human’s life. So it is impossible to
review all the literatures related to it. So in this chapter we
will focus on the main research methodologies which are
mostly related to my proposed work.
In 1966, the first attempt to construct a semi-automated
face recognition human computer system was made [1],
[2]. The system was based on the extraction of the
coordinates of a set of features from the photographs,
which were then used by the computer for recognition.
Later, feature extraction and pattern classification
techniques [3] were employed for face recognition
purposes. In [4] and [5], a template matching approach
was developed and improved, using automatic feature
measurements and deformable templates which are
parameterized models of face.
1970s, Goldstein, Harmon, and Lesk used 21 specific
subjective markers such as hair color and lip thickness to
automate the recognition. The problem with both of these](https://image.slidesharecdn.com/irjet-v5i6311-180809062948/85/IRJET-A-Survey-on-Face-Recognition-based-Security-System-and-its-Applications-1-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 06 | June-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1665
early was that the measurements and locations were
manually computed.
In 1988, Kirby and Sirovich applied principle component
analysis, a standard linear algebra technique, to the face
recognition problem. This was considered somewhat of a
milestone as it showed that less than one hundred values
were required to accurately code a suitably aligned and
normalized face image.
Early 1990s have witnessed the beginning of a new wave
of developments for face recognition, with considerable
research endeavors made for enhancing recognition
performance. These include principal component analysis
(PCA) [6].
Abdullah, et al, in their research [7] tried to minimize the
participated eigenvectors which consequently decreases
the computational time. They conduct a study to optimize
the time complexity of PCA (eigenfaces) that does not
affects the recognition performance.
Arora in (2012) implemented eigenfaces recognition
algorithm for real time face recognition in [9] using laptop
computer and web camera, Arora considered video frames
as still picture, his experiment examined changing or
variation in illumination and head size, he considered the
experiment quite successful. Results of Arora’s experiment
where registered as following:
Table -1: Results for eigenfaces algorithm for real time
face recognition (Arora, 2012, 196)
Face Condition
Recognition
Accuracy
Recognition
Error
Normal 83% 17%
Light Variation 61% 39%
Size of Face
variation
55% 45%
2. APPLICATIONS OF FACE RECOGNITION SYSTEM
a) Face Identification: Face recognition systems
identify people by their face images. Face
recognition systems establish the presence of an
authorized person rather than just checking
whether a valid identification (ID) or key is being
used or whether the user knows the secret
personal identification numbers (Pins) or
passwords. For example to eliminate duplicates in
a nationwide voter registration system because
there are cases where the same person was
assigned more than one identification number.
The face recognition system directly compares the
face images of the voters and does not use ID
numbers to differentiate one from the others.
When the top two matched faces are highly
similar to the query face image, manual review is
required to make sure they are indeed different
persons so as to eliminate duplicates.
b) Access Control: Access control is a way of
limiting access to a system or to physical or
virtual resources. In computing, access control id
a process by which users are granted access and
certain privileges to system, resources or
information.
c) Security: Today more than ever, security is a
primary concern at airports and for airline staff
office and passengers. Airport protection systems
that use face recognition technology have been
implemented at many airports around the world.
The following are the two examples
d) Image database investigations: Searching image
databases of licensed drivers benefit recipients,
missing children, immigrants and police bookings.
3. FACE RECOGNITION METHODS
In beginning Face Recognition was treated as 2D pattern
recognition. The distance between important points where
used to recognize known faces example: measuring the
distance between the eyes or other important points or
measuring different angles of facial comparison, the
following methods are used for face recognition:
a) Holistic Matching Method: In this method the
complete face region is taken into account as
input data into face catching system. One of the
best example of holistic method are Eigen faces,
principal component analysis (PCA), linear
discriminant analysis (LDA), independent
component analysis (IDA) etc.
b) Feature based Matching: In this method local
feature such as eyes, nose & mouth are first of all
extracted and their location and local statistics are
fed into structural classifier. Big challenge is face
restoration. Feature based distinguishes between
three different extraction methods
i. Generic methods based on edges, lines &
curves.
ii. Feature template based method.
iii. Structural matching methods that take
into consideration geometrical
constraints on the features
c) Hybrid Method: It uses a combination of both
Holistic and Feature based method. Generally 3D
images are used.](https://image.slidesharecdn.com/irjet-v5i6311-180809062948/85/IRJET-A-Survey-on-Face-Recognition-based-Security-System-and-its-Applications-2-320.jpg)
![International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 05 Issue: 06 | June-2018 www.irjet.net p-ISSN: 2395-0072
© 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1666
3. CONCLUSIONS
Face recognition is a challenging problem in the field of
image processing. Because of lots of application in
different fields the face recognition has received great
attention. In today’s networked world, the necessity of
maintaining information safety as well as preserving the
physical property is gradually becoming significant and
tedious. As the requirement of high level of security arises,
face recognition technology is bound to cope with the
upcoming needs. Also, face recognition has caught the eye
of researchers in the areas ranging from image processing
and security to computer vision. Since it maintain our
privacy and protect our assets without dropping our
identity. Therefore, face recognition deals with people as
its centre of attention and thereby increasing the user-
friendliness in human-computer interaction.
REFERENCES
[1] Saudargare, P.V., & chaudhari, D.S. (2012). Facial
expression recognition using neural network- An
overview , International Journal of soft computing and
engineering (IJSCE), 2(1),224-227.M. Young, The
Technical Writer’s Handbook. Mill Valley, CA:
University Science, 1989.
[2] Slavkovic, M., & Jevtic, D. (2012). Face Recognition
Using Eigenface Approach. Serbian Journal of Electrical
Engineering, 9(1), 121-130. Süsstrunk, S., & Buckley R.,
&Swen, S. (1999).Standard RGB Color Spaces.
[3] Chitra, S., & Balakrishnan, G. (2012). Comparative
Study for Two Color Spaces HSCbCr and YCbCr in Skin
Color Detection, Applied Mathematical Sciences, 6(85),
4229 – 4238. Different Face Recognition Algorithms.
BIOINFO Medical Imaging, 1(1), 05-09.
[4] Pathak, V., & Patwari, D.N., & Khanale, P.B., & Tamboli,
N.M., &Pathak, V. M. (2011). Study and Comparison of
Different Face Recognition Algorithms. BIOINFO
Medical Imaging, 1(1), 05-09.
[5] Ramesha, K. (2009). Advanced Biometric Identification
on Face, Gender and Age Recognition, IEEE journal,
(978-0-7695-3845-7/09), 10.1109.
[6] Thepade, S., & Khandelwal, S., & Dhamejani, K., & Azmi,
A. (2012). Improved Face Recognition with Multilevel
BTC using Kekre’s LUV Color Space, (IJACSA)
International Journal of Advanced Computer Science
and Applications, 3(1), 156-160.
[7] Abdullah, M., & Wazzan, M., & Bo-saeed, S. (2012).
Optimizing face recognition using PCA, International
Journal of Artificial Intelligence & Applications
(IJAIA),3(2),(23-31), 10.5121/ijaia.2012.3203 23.
[8] Ramesha, K. (2009). Advanced Biometric Identification
on Face, Gender and Age Recognition, IEEE journal,
(978-0-7695-3845-7/09), 10.1109.
[9] Arora, K. (2012). Real Time Application of Face
Recognition concept, International Journal of Soft
Computing and Engineering (IJSCE), 2 (5),2231-2307.
[10]Abul-Kashem, M., & Akhter, M. N., & Ahmed, S., & Alam,
M. M., (2011), Face Recognition System Based on
Principal Component Analysis (PCA) with Back
Propagation Neural Networks (BPNN),Canadian
Journal on Image Processing and Computer Vision.
2(4), 36-45.
[11] Chakraborty, D. (2012). An Illumination invariant face
detection based on human shape analysis and skin
color information. Signal & Image Processing: An
International Journal (SIPIJ), 3, 55-62](https://image.slidesharecdn.com/irjet-v5i6311-180809062948/85/IRJET-A-Survey-on-Face-Recognition-based-Security-System-and-its-Applications-3-320.jpg)
IRJET-A Survey on Face Recognition based Security System and its Applications
- 1. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 06 | June-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1664 A Survey on Face Recognition based security system and its applications Nijara Kalita1, L.P.Saikia 2 1 MTech Computer Science & Engg , Assam Downtown University, India 2Professor, Computer Science & Engg , Assam downtown University, India ---------------------------------------------------------------------***--------------------------------------------------------------------- Abstract - Face is our primary focus of attention and it plays an important role in conveying identity and emotions. We meet numbers of faces throughout our lifetime but it is quite robust to identify despite of variation in visual stimulus due to changing condition such as aging, beard, glasses or changes in hairstyle. Therefore Face Recognition system is a technology which is capable of identifying or verifying a person from a digital image or a video frame from a video source. Face recognition presents a challenging problem in the process of image analysis and computer vision. This paper describes FR, its definition, a brief history about it, Challenges in FR, Face Recognition methods and the various applications that are now in used in the modern trends. Key Words: Face Recognition, Eigenfaces, Image processing, Face Detection, Principal Component Analysis. 1. INTRODUCTION Face Recognition has becoming one of the most biometrics authentication techniques from the last few years. Mainly the Face Recognition system has two tasks: one is verification and the other is identification. Face verification means 1:1 match that is verification authenticates an individual by comparing one specific biometric stored in the database, while identification means comparing all the biometrics stored in the database. Therefore face identification means 1: N match. Machine Recognition of faces is very important now-a-days because of the commercial and law enforcement applications such as forensic identification, access control, and border control. The human face plays an important role in our social interaction, conveying people’s identity. Using the human face as a key to security, biometric face recognition technology has received significant attention in the past several years due to its potential for a wide variety of applications in both law enforcement and non-law enforcement. 1.1 Definitions Face Recognition is the process of capable of uniquely identifying or verifying a person by comparing and analyzing patterns based on the person's facial contours. Now-a-days Face Recognition is mostly used for security purposes, though there is increasing interest in other areas of use. In fact, face recognition technology has received significant to law enforcement as well as other enterprises. Human face plays a very important role in our social interactions and in conveying people’s identity. Using the human face as a key to security, face recognition technology has received a significant attention in the past several years due to its potential for a wide variety of applications in the research fields’ attention as it has potential for a wide range of application related. A face recognition system can be divided into three major steps: a) Face Detection: Face detection is the necessary first step in a face recognition system. The main aim of this step is to determine whether a human face appears in a given image. b) Features Extraction: The main aim of this step is to extract face component features like eyes, nose, mouth, etc from human face image. Feature extraction is very much important for the initialization of processing techniques like face tracking, facial expression recognition or face recognition c) Face Recognition: The main aim of face recognition is to identify a face from the images in the database. 1.2 History Face detection and recognition had a huge number of researches because of its important applications in all fields of society as well human’s life. So it is impossible to review all the literatures related to it. So in this chapter we will focus on the main research methodologies which are mostly related to my proposed work. In 1966, the first attempt to construct a semi-automated face recognition human computer system was made [1], [2]. The system was based on the extraction of the coordinates of a set of features from the photographs, which were then used by the computer for recognition. Later, feature extraction and pattern classification techniques [3] were employed for face recognition purposes. In [4] and [5], a template matching approach was developed and improved, using automatic feature measurements and deformable templates which are parameterized models of face. 1970s, Goldstein, Harmon, and Lesk used 21 specific subjective markers such as hair color and lip thickness to automate the recognition. The problem with both of these
- 2. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 06 | June-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1665 early was that the measurements and locations were manually computed. In 1988, Kirby and Sirovich applied principle component analysis, a standard linear algebra technique, to the face recognition problem. This was considered somewhat of a milestone as it showed that less than one hundred values were required to accurately code a suitably aligned and normalized face image. Early 1990s have witnessed the beginning of a new wave of developments for face recognition, with considerable research endeavors made for enhancing recognition performance. These include principal component analysis (PCA) [6]. Abdullah, et al, in their research [7] tried to minimize the participated eigenvectors which consequently decreases the computational time. They conduct a study to optimize the time complexity of PCA (eigenfaces) that does not affects the recognition performance. Arora in (2012) implemented eigenfaces recognition algorithm for real time face recognition in [9] using laptop computer and web camera, Arora considered video frames as still picture, his experiment examined changing or variation in illumination and head size, he considered the experiment quite successful. Results of Arora’s experiment where registered as following: Table -1: Results for eigenfaces algorithm for real time face recognition (Arora, 2012, 196) Face Condition Recognition Accuracy Recognition Error Normal 83% 17% Light Variation 61% 39% Size of Face variation 55% 45% 2. APPLICATIONS OF FACE RECOGNITION SYSTEM a) Face Identification: Face recognition systems identify people by their face images. Face recognition systems establish the presence of an authorized person rather than just checking whether a valid identification (ID) or key is being used or whether the user knows the secret personal identification numbers (Pins) or passwords. For example to eliminate duplicates in a nationwide voter registration system because there are cases where the same person was assigned more than one identification number. The face recognition system directly compares the face images of the voters and does not use ID numbers to differentiate one from the others. When the top two matched faces are highly similar to the query face image, manual review is required to make sure they are indeed different persons so as to eliminate duplicates. b) Access Control: Access control is a way of limiting access to a system or to physical or virtual resources. In computing, access control id a process by which users are granted access and certain privileges to system, resources or information. c) Security: Today more than ever, security is a primary concern at airports and for airline staff office and passengers. Airport protection systems that use face recognition technology have been implemented at many airports around the world. The following are the two examples d) Image database investigations: Searching image databases of licensed drivers benefit recipients, missing children, immigrants and police bookings. 3. FACE RECOGNITION METHODS In beginning Face Recognition was treated as 2D pattern recognition. The distance between important points where used to recognize known faces example: measuring the distance between the eyes or other important points or measuring different angles of facial comparison, the following methods are used for face recognition: a) Holistic Matching Method: In this method the complete face region is taken into account as input data into face catching system. One of the best example of holistic method are Eigen faces, principal component analysis (PCA), linear discriminant analysis (LDA), independent component analysis (IDA) etc. b) Feature based Matching: In this method local feature such as eyes, nose & mouth are first of all extracted and their location and local statistics are fed into structural classifier. Big challenge is face restoration. Feature based distinguishes between three different extraction methods i. Generic methods based on edges, lines & curves. ii. Feature template based method. iii. Structural matching methods that take into consideration geometrical constraints on the features c) Hybrid Method: It uses a combination of both Holistic and Feature based method. Generally 3D images are used.
- 3. International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 05 Issue: 06 | June-2018 www.irjet.net p-ISSN: 2395-0072 © 2018, IRJET | Impact Factor value: 7.211 | ISO 9001:2008 Certified Journal | Page 1666 3. CONCLUSIONS Face recognition is a challenging problem in the field of image processing. Because of lots of application in different fields the face recognition has received great attention. In today’s networked world, the necessity of maintaining information safety as well as preserving the physical property is gradually becoming significant and tedious. As the requirement of high level of security arises, face recognition technology is bound to cope with the upcoming needs. Also, face recognition has caught the eye of researchers in the areas ranging from image processing and security to computer vision. Since it maintain our privacy and protect our assets without dropping our identity. Therefore, face recognition deals with people as its centre of attention and thereby increasing the user- friendliness in human-computer interaction. REFERENCES [1] Saudargare, P.V., & chaudhari, D.S. (2012). Facial expression recognition using neural network- An overview , International Journal of soft computing and engineering (IJSCE), 2(1),224-227.M. Young, The Technical Writer’s Handbook. Mill Valley, CA: University Science, 1989. [2] Slavkovic, M., & Jevtic, D. (2012). Face Recognition Using Eigenface Approach. Serbian Journal of Electrical Engineering, 9(1), 121-130. Süsstrunk, S., & Buckley R., &Swen, S. (1999).Standard RGB Color Spaces. [3] Chitra, S., & Balakrishnan, G. (2012). Comparative Study for Two Color Spaces HSCbCr and YCbCr in Skin Color Detection, Applied Mathematical Sciences, 6(85), 4229 – 4238. Different Face Recognition Algorithms. BIOINFO Medical Imaging, 1(1), 05-09. [4] Pathak, V., & Patwari, D.N., & Khanale, P.B., & Tamboli, N.M., &Pathak, V. M. (2011). Study and Comparison of Different Face Recognition Algorithms. BIOINFO Medical Imaging, 1(1), 05-09. [5] Ramesha, K. (2009). Advanced Biometric Identification on Face, Gender and Age Recognition, IEEE journal, (978-0-7695-3845-7/09), 10.1109. [6] Thepade, S., & Khandelwal, S., & Dhamejani, K., & Azmi, A. (2012). Improved Face Recognition with Multilevel BTC using Kekre’s LUV Color Space, (IJACSA) International Journal of Advanced Computer Science and Applications, 3(1), 156-160. [7] Abdullah, M., & Wazzan, M., & Bo-saeed, S. (2012). Optimizing face recognition using PCA, International Journal of Artificial Intelligence & Applications (IJAIA),3(2),(23-31), 10.5121/ijaia.2012.3203 23. [8] Ramesha, K. (2009). Advanced Biometric Identification on Face, Gender and Age Recognition, IEEE journal, (978-0-7695-3845-7/09), 10.1109. [9] Arora, K. (2012). Real Time Application of Face Recognition concept, International Journal of Soft Computing and Engineering (IJSCE), 2 (5),2231-2307. [10]Abul-Kashem, M., & Akhter, M. N., & Ahmed, S., & Alam, M. M., (2011), Face Recognition System Based on Principal Component Analysis (PCA) with Back Propagation Neural Networks (BPNN),Canadian Journal on Image Processing and Computer Vision. 2(4), 36-45. [11] Chakraborty, D. (2012). An Illumination invariant face detection based on human shape analysis and skin color information. Signal & Image Processing: An International Journal (SIPIJ), 3, 55-62