Integrated Intelligent Research (IIR) International Journal of Web Technology

Volume: 04 Issue: 02 December 2015 Page No.100-102

ISSN: 2278-2389

Facial Feature Recognition Using Biometrics

Brindha T,MS Josephine
Research scholar,Dr MGR Research institute and Educational University,Maduravoyal, Chennai
Prof Dept of MCA,Dr MGR Research institute and Educational University,Maduravoyal, Chennai
[email protected]

Abstract-Face recognition is one of the few biometric methods million in losses. In most of these crimes, the criminals were
that possess the merits of both high accuracy and low aware taking advantage of a fundamental flaw in the
intrusiveness. Biometric requires no physical interaction on conventional access control systems. The systems do not grant
behalf of the user. Biometric allows to perform passive access by “who we are”, but by “what we have”, such as ID
identification in a one to many environments. Passwords and cards, keys, passwords, PIN numbers, or mother’s maiden
PINs are hard to remember and can be stolen or guessed; name. None of these means really define us. Rather, it is a
cards, tokens, keys and the like can be misplaced, forgotten, means to authenticate us. This technology is based in a field
purloined or duplicated; magnetic cards can become corrupted called “biometrics”. Biometric access control are automated
and unreadable. However individuals biological traits cannot methods of verifying or recognizing the identity of a living
be misplaced, forgotten, stolen or forged. person on the basis of some physiological characteristics, such
as finger prints or facial features, or some aspects of the
Keywords— Face recognition, low intrusiveness, corrupted, persons behavior like his/her handwriting style or key stroke
Pins patterns. Since biometric systems identify a person by
biological characteristic they are difficult to forge.A biometric
I. INTRODUCTION is a unique, measurable characteristic of a human being that
Face recognition is not perfect and struggles to perform under can be used to automatically recognize an individual or verify
certain condition. A researcher at the Carnegie Mellon an individual’s identity. Biometrics can measure both
Robotics Institute, describe one obstacle “Face recognition has physiological and behavioral characteristics. Physiological
been getting pretty good at full frontal faces and 20 degrees biometrics (based on measurements and data derived from
off, but as soon as u go towards profile, there have been direct measurement of a part of the human body) include:
problems”.Other conditions where face recognition does not a. Finger-scan
work will include poor lighting, sunglasses, long hair or other
objects partially covering the subjects face and low resolution b. Facial Recognition
images. Another serious disadvantage is that many systems are c. Iris-scan
less effective if facial expressions vary. The effectiveness is d. Retina-scan
critics of the technology complain that the London borough of e. Hand-scan
New ham giving disappointing results. User interface captures Behavioral biometrics (based on measurements and data
the analog or digital image of the persons face. In the derived from an action) include:
enrollment module the obtained sample is preprocessed and a. Voice-scan
analyzed. This analyzed data is stored in the database for the b. Signature-scan
purpose of future comparison.As compared with other c. Keystroke-scan
biometrics systems using finger print/palm print and iris, face A “biometric system” refers to the integrated hardware and
recognition has distinct advantages because of its non-contact software used to conduct biometric identification or
process. Face images can be captured from a distance without verification. Anonymously and passively captures passenger’s
touching the person being identified and the identification facial features as they enter airport and then tracks them
does not require interacting with the person. It uses existing through their journey. Face recognition is one of the few
hardware infrastructure, existing cameras and image capture. biometric methods that possess the merits of both high
Devices will work with no problems. In addition, face accuracy and low intrusiveness.
recognition serves the crime deter rant purpose because face
images that have been recorded and archived can later help II. FACE RECOGNITION OVER OTHER
identify a person.Face recognition technology may solve this BIOMETRIC
problem since a face is undeniably connected to its owner
except in the case of identical twins. It’s non-transferable. The In this section we review the features that are used for face
system can then compare scans to records stored in a central or recognition section 2 discusses the face for recognition.
local database or even on a smart card.
A. Face recognition features
Face recognition is one of the few biometric methods that
possess the merits of both high accuracy and low There are number reasons to choose face recognition. This
intrusiveness. From time to time we hear about the crimes of includes the following
credit card, fraud, and computer break-ins by hackers, security a. It requires no physical interaction on behalf of the user.
breaches in a company or government building. In the year
1998, sophisticated cyber crooks caused well over US$100
100
Integrated Intelligent Research (IIR) International Journal of Web Technology
Volume: 04 Issue: 02 December 2015 Page No.100-102
ISSN: 2278-2389
b. It is accurate and allows for high enrolment and verification
rates.
c. It does not require an expert to interpret the comparison
result.
d. It can use your existing hardware infrastructure, existing
cameras and image capture
Devices will work with no problems a. b. c.
e. It is the only biometric that allow you to perform passive
identification in a one to many environments (e.g.: identifying
a terrorist in a busy Airport terminal). People are more
comfortable signing their names or speaking to a microphone
than placing their eyes before a scanner or giving a drop of
blood for DNA sequencing. Passwords and PIN’s are hard to
remember and can be stolen or guessed; cards, tokens, keys
and the like can be misplaced, forgotten , purloined or
duplicated; magnetic cards can become corrupted and
unreadable. However, and individual’s biological traits cannot d. e. f.
be misplaced, forgotten, stolen or forged.
Figure 2. Features of the face

The figure 2 includes facial features of different persons.

Figure 2 a. showing a female having front fore head with
hair.The figure 2b. with person with hair at front and having
spectacles worn. Figure 2 c. having bald at front face.Figure
2d. showing the face of a male having bulged chin.Figure 2e.
a. b. c. showing the face of male with thick spectacles. Figure 2 f.
showing the person of male with hair at forehead .From time
to time we hear about the crimes of credit card, fraud, and
computer break-in-ins by hackers, security breaches in a
company or government building in the year 1998,
sophisticated cyber crooks caused well over US$100 million
in loss. In most of these crimes, the criminals were taking
advantage of a fundamental flaw in the conventional access
control systems. The systems do not grant access by “who we
d e. f. are “, but by “ what we have”, such as ID cards, keys,
passwords, PIN numbers or mother’s maiden name. None of
Figure 1. Face for recognition these means really define us. Rather, it is a means to
authenticate us. This technology is based in a field called
The facial identification is based on facial features left eye “biometrics”. Biometric access control are automated methods
and the right eye, eyebrow, position of the nose, position of of verifying or recognizing living person on the basis of some
the mouth, chin shape, face width at nose position and face physiological characteristics, such as finger prints or facial
width halfway between nose tip and eyes. Figure 1 shows the features , or some aspects of the persons behaviour like his/
features for recognition.Biometric based technologies include her handwriting style or key stroke patterns. Since biometric
identification based on physiological characteristics (such as systems identify a person by biological characteristic they are
face, fingerprints, finger geometry, hand geometry, hand difficult to forge.
veins, palm iris, retina, ear and voice) and behavioral traits
(such as gait, signature and key stroke dynamics).Face B. Use face for recognition
recognition appears to offer several advantages over other
biometric methods, a few of which are outlined here: all the People are more comfortable signing their names or speaking
technologies require voluntary action by the user.As compared to a microphone than placing their eyes before a scanner or
with other biometrics systems using finger print/palm and iris giving a drop of blood for DNA sequencing. Passwords and
face recognition has distinct advantages because of its non- PIN’s are hard to remember and can be stolen or guessed;
contact process. Face images can be captured from a distance cards, tokens, keys, and the like can be misplaced, forgotten,
without touching the person being identified and the purloined or duplicated; magnetic cards can become corrupted
identification does not require interacting with the person. In and unreadable. However, an individual’s biological traits
addition, face recognition serves the crime deterrent purpose cannot be misplaced, forgotten, stolen or forged.Face
because face images that have been recorded and archived can recognition appears to offer several advantages over other
later help identify a person.Anonymously and passively biometric methods, a few of which are outlined here: All the
captures passenger’s facial features as they enter airport and technologies require voluntary action by the user. The human
then tracks them through their journey. Face recognition is one face plays an important role in our social interaction,
of the few biometric methods that possess the merits of both conveying people’s identity. Using the human face as a key to
high accuracy and low intrusiveness. security, biometric face recognition technology has received

101
Integrated Intelligent Research (IIR) International Journal of Web Technology
Volume: 04 Issue: 02 December 2015 Page No.100-102
ISSN: 2278-2389
significant attention in the past several years due to its
potential for a wide variety of applications in law enforcement
and non-law enforcement.As compared with other biometrics
systems using finger print/palm print & iris face recognition
has distinct advantages because of its non-contact process.
Face images can be captured from a distance without touching
the person being identified, and the identification does not
require interacting with the person being identified, and the
identification does not require interacting with the person. In
addition, face recognition serves the crime deterrant purpose
because face images that have been recorded and archived can
later help identify a person.Biometric can measure both
physiological and behavioral characteristics. Face recognition
technologies have been associated generally with every costly
top secure applications. Today the core technologies have
evolved and the cost of equipment’s is going down due to the
increasing processing power. Certain applications of face
recognition technology are now cost effective, reliable and
highly accurate.
III. CONCLUSION

This paper discusses the unique measurable characteristic of a

human being that can be used automatically recognize an
individual or verify an individual’s identity. Face recognition
technologies have been associated generally with every costly
top secure applications. In pattern recognition the feature
extraction is one technique that is widely deployed due to its
user friendliness.

REFERENCES

[1] Jain ,A.K.,Kumar,A.,2012 Biometric recognition: An overview, in :

my ordim,E .,Tzovaras, D.(Eds), second generation Biometric: The
ethical, legal and social context. Springer Netherlands Volume II of
The International Library of Ethics, Law and Technology, pp 49-79.
[2] Math Works MATLAB, 2013. Computer Vision System Toolbox:
2013b - Video Stabilization Using Point Feature Matching. The Math
Works Inc., Natick, Massachusetts, United States.
[3] T Wang, P Shi, Kernel Grassmannian distances and discriminant
analysis for face recognition from image sets. Pattern Recogn.Lett.
30(13), 1161-1165(2009)
[4] K Koh, SJ Kim, S Boyd, l1_ls: simple Mat lab solver for l1-
regularized least squares
problems,(2008).http://www.stanford.edu/~boyd/l1_ls/.Accessed 13
January 2014
[5] K Fukui,O Yamaguchi, Face recognition using multi-viewpoint
patterns for robot vision, in Robotics Research, ed. By Dario, R Chatila
(Springer, Heidelberg, 2005), pp.192-201
[6] Zhifeng Li, Member, IEEE, Unsang Park and Anil K.Jain ‘A
Discriminative Model for Age Invariant Face Recognition’
[7] Young H.Kwon and Niels da Victoria Lobo ‘Age Classification from
Facial Images’

102