See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/283491468

International Journal of Advanced Research in Computer Science and Software

Engineering

Research · November 2015

DOI: 10.13140/RG.2.1.1512.6480

CITATIONS READS

2 4,501

1 author:

Muzhir Al-Ani
University of Human Development, Sulaymaniyah
138 PUBLICATIONS   345 CITATIONS   

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Effective fingerprint recognition approach based on double fingerprint thumb View project

Design and Implementation of Broken Blister Detection Approach View project

All content following this page was uploaded by Muzhir Al-Ani on 04 November 2015.

The user has requested enhancement of the downloaded file.

 Volume 5, Issue 9, September 2015 ISSN: 2277 128X
International Journal of Advanced Research in
Computer Science and Software Engineering
Research Paper
Available online at: www.ijarcsse.com
An Efficient Approach for Human Face Recognition
1
Dr. R. Satya Prasad, 2Muzhir Shaban Al-Ani, 3Salwa Mohammed Nejres
1, 3
Department of Computer Science & Engineering, Acharya Nagrjuna University,
Nagarjuna Nagar, Guntur, Andhra Pradesh India
2
Department of Computer Science, Anbar University CS College, Anbar, Iraq

Abstract-Face recognition is one of the important fields for their wide range of applications in different areas. Our job
is to implement an efficient approach for human face recognition. This paper presents an efficient approach to
address the representation issue and the matching issue in face recognition process. The implemented face
recognition approach is concentrated on the image performance in order to generate required features from the face
image. The obtained result indicated a good performance of face image is generated from the tested system.

Keywords: face detection, face recognition, face identification,

I. INTRODUCTION
As biometric technologies are improved very fast, so many devices and applications are introduced in the recent
years.Face recognition is a broad interdisciplinary nature of the interest such as: computer recognition and pattern
recognition; biometrics and security; multimedia processing and computer vision; psychology and neuroscience. It is a
field of research that complain the necessity of interaction between computer scientists and psychologists.Everyone has a
face and everyone readily displays the face, so face recognition has the advantage of ubiquity and of being universal over
other major biometrics. Face recognition also has the advantage that the acquisition devices are cheap and are becoming a
commodity.Face recognition has been employed in wide range security related applications such as surveillance, airports,
organizations, banks, mug shot identification, e-passport, and access control.Although face recognition has made huge
progress in the recently, there have been several concerns preventing its wider deployment, such as the effectiveness in
field test, the performance under uncontrolled conditions, and privacy concern [1,2].

II. FACE RECOGNITION STANDARD

Many identification systems comprise three elements [3]:
 attributed identifiers (such as name, Social Security number, bank account number, and driver’s license number)
 biographical identifiers (such as address, profession, and education)
 biometric identifiers (such as photographs and fingerprint).
The facial recognition process normally has four interrelated phases or steps as shown in Figure (1) [4].
 the first step is face detection
 the second is normalization
 the third is feature extraction
 the fourth cumulative step is face recognition.

These steps depend on each other and often use similar techniques.

Figure (1) facial recognition process

III. RELATED WORKS

Many algorithms and approaches are published in this field of face recognition andwe will concern some of the resent
researches:
RabiaJafri and Hamid R. Arabnia (2009), provided an overview of the well-known methods in each of these
categories and some of the benefits and drawbacks of the schemes mentioned therein are examined. Then, a discussion
outlining the incentive for using face recognition, the applications of this technology, and some of the difficulties
plaguing current systems with regard to this task has also been provided. This paper also mentioned some of the
© 2015, IJARCSSE All Rights Reserved Page | 133
 Prasad et al., International Journal of Advanced Research in Computer Science and Software Engineering 5(9),
September- 2015, pp. 133-136
propselalgorithms developed for this purpose and attempts to give an idea of the state of the art of face recognition
technology [5].
S.B.Thorat et al. (2010), focused on 3-D facial recognition system and biometric facial recognition system. We do
critics on facial recognition system giving effectiveness and weaknesses. This paper also introduces scope of recognition
system in India. There are some weaknesses of facial recognition system, there is a tremendous scope in India. This
system can be effectively used in ATM’s, identifying duplicate voters, passport and visa verification, driving license
verification, in defense, competitive and other exams, in governmentand private sectors. As a result there are no
technological or financial barriers for stepping from the pilot project to widespread deployment [6].
MuzhirShaban Al-Ani1 and AlaaSulaiman Al-Waisy (2011), presented an efficient approach using a kernel machine
based approach for learning such nonlinear mappings to provide effective view-based representation for multi-view
face detection. In this paper Kernel Principal Component Analysis (KPCA) is used to project data into the view-
subspaces then computed as view-based features. Multi-view face detection is performed by classifying each input
image into face or non-face class, by using a two class Kernel Support Vector Classifier (KSVC). Experimental
results demonstrate successful face detection approach over a wide range of facial variation in color, illumination
conditions, position, scale, orientation, 3D pose, and expression in images from several photo collections [7].
MuzhirShaban Al-Ani1 and AlaaSulaiman Al-waisy (2012), proposed a novel face recognition approach based on
wavelet-curvelet technique. This algorithm based on the similarities embedded in the images that utilize the wavelet-
curvelet technique to extract facial features. The implemented technique can overcome on the other mathematical image
analysis approaches. This approaches may suffered from the potential for a high dimensional feature space,
Therefore, it aims to reduce the dimensionality that reduce the required computational power and memory size. Then
the Nearest Mean Classifier (NMC) is adopted to recognize different faces. In this work, three major experiments
were done. Two face databases (MAFD & ORL, and higher recognition rate is obtained by the implementation of this
techniques [8]).
Wonjun Hwanget at. (2013), proposed a novel unifying framework using a Markov network to learn the relationship
between multiple classifiers in face recognition. They assumed that we have several complementary classifiers and assign
observation nodes to the features of a query image and hidden nodes to the features of gallery images. They connected
each hidden node to its corresponding observation node and to the hidden nodes of other neighboring classifiers. For each
observation hidden node pair, they collected a set of gallery candidates that are most similar to the observation instance,
and the relationship between the hidden nodes is captured in terms of the similarity matrix between the collected gallery
images. Posterior probabilities in the hidden nodes are computed by the belief propagation algorithm [9].
Patrick Grother and Mei Ngan (2014),tracked that improvement of face recognition technologies and its conduct of
regular independent, free, open, and public evaluations has fostered improvements in the state of the art. One-to-many
face identification systems are mostly used in conjunction with trained human facial reviewers. The systems are
configured to operate in two regimes: first, with a low threshold that necessitates adjudication of many false positive
candidates by a reviewer specifically employed to do so; second, with a high threshold, in which false positive outcomes
are rare and human intervention is only needed infrequently. Low false positive rates are accompanied by higher false
negative rates [10].

IV. IMPLEMENTED APPROACH

As we mentioned above any face recognition system can be implemented via four steps, these steps are: face detection,
normalization, feature extraction then face recognition. Feature extraction is the most important step in the recognition
system. The implemented approach concentrated on the feature extraction process in which highlights and increases the
face performance. The overall face recognition system can be implemented via many steps as shown in figure (2):
 Step 1: Color to Gray Scale Conversion, this step is started after the face image acquisition process in which the
color face image in converted into gray scale face image.
 Step 2: Image Enhancement, this is an important step to highlight the face image details, in which we applied
histogram equalization that redistributed the pixels over the image scale.
 Step 3: Image Resizing, this step aims to standardized the face image size in order to be compatible with the
overall system.
 Step 4: 3rd Level 2D_DWT, in this step three levels of two dimensional discrete wavelet transform (2D DWT)
are applied to the resized image in order to extract the required features. The implemented system goes in details
to generate suitable features that required for the decision.Daubechiesare selected as wavelet families to be the
best wavelet used for the system.

Figure (2) implemented face recognition algorithm

© 2015, IJARCSSE All Rights Reserved Page | 134
 Prasad et al., International Journal of Advanced Research in Computer Science and Software Engineering 5(9),
September- 2015, pp. 133-136
V. RESULTS AND ANALYSIS
After application of all steps of the implemented system we demonstrate the results in each step. The gray scale image is
resized and selected the face image; this image and their histogram are shown in figure (3). Then an equalized histogram
is implemented to the resized image in order to highlight the face details, this image and their histogram also are shown
in figure (3), in which we can see that there is a normal distribution of pixels of the face image.
Resized Gray Scale Image Histogram of Resized Gray Scale Image

15000
500
10000

1000 5000

1500 0
200 400 600 800 0 100 200
4
Equalized Resized Image xHistogram
10 of Equalized Image

2
500

1
1000

1500 0
200 400 600 800 0 100 200
Figure (3) resized gray scale image and equalized histogram

The feature extraction step is the main core of the implemented system, in which we applied the 3 rd level two
dimensional discrete wavelet transform and the Daubechies are selected as wavelet families to be implemented. These
levels are implemented via db2 and these levels are demonstrated in figure (4). The decomposition of 2D discrete wavelet
transform of the used face image is shown in figure (5).
LL Third Level Approximation LL Second Level Approximation

50 100

100 200

150 300

20 40 60 80 100 50 100 150 200

LL First Level Approximation Resized Gray Scale Image

200
500

400
1000
600

1500
100 200 300 400 200 400 600 800
rd
Figure (4) applying of 3 level discrete wavelet transform

Original Image Approximation coef. at level 3

200

400

600

800

1000

1200

1400

200 400 600 800

dwt
Synthesized Image Image Selection

idwt

Decomposition at level 3

Figure (5) 2D wavelet decomposition

© 2015, IJARCSSE All Rights Reserved Page | 135
 Prasad et al., International Journal of Advanced Research in Computer Science and Software Engineering 5(9),
September- 2015, pp. 133-136
VI. CONCLUSIONS
Face recognition algorithms are faced with many problems such as ages, directions, orientations, background, lighting,
…etc. In this project many face images are collected via simple digital camera, in addition multiple face images are
collected for each person. We proposed an efficient approach for human face recognition in which it used 3 rd level of
Daubechies wavelet families.The implemented approach gives an accurate recognition results in addition a big
reduction of the image dimensions that reduce the required computation and memory consumption.

REFERENCES
[1] Rama Chellappa, Charles L. Wilson, and SaadSirohey. Human and Machine Recognition of Faces: A Survey.
Proceedings of the IEEE, 83(5):705–740, May 1995.
[2] Stan Z. Li and Anil K. Jain, “Introduction,” in Hand-book of Face Recognition, Stan Z. Li and Anil K. Jain, Eds.
2004, pp. 1–11, Springer-Verlag.
[3] Heisele, B., P. Ho, J. Wu, T. Poggio. “Face recognition: component-based versus global approaches.”
Computer Vision and Image Understanding. 91.1 (2003): 6-21.
[4] Phillips, P. J., A. Martin, C. L. Wilson, and M. Przybocki. “An Introduction to Evaluating Biometric
Systems.” Computer, 33.2 (2000): 56-63.
[5] RabiaJafri and Hamid R. Arabnia, “A Survey of Face Recognition Techniques”, Journal of Information
Processing Systems, Vol.5, No.2, June 2009.
[6] S.B.Thorat, S.K.Nayak and Jyoti P Dandale, “Facial Recognition Technology: An analysis with scope in India”,
International Journal of Computer Science and Information Security, Vol. 8, No. 1, 2010.
[7] MuzhirShaban Al-Ani1 and AlaaSulaiman Al-Waisy (2011), “Multi-View Face Detection Based On Kernel
Principal Component Analysis and Kernel Support Vector Techniques”, International Journal on Soft
Computing ( IJSC ), Vol.2, No.2, May 2011.
[8] MuzhirShaban Al-Ani1 and AlaaSulaiman Al-waisy, “Face Recognition Approach Based On Wavelet –
Curvelet Technique”, Signal & Image Processing : An International Journal (SIPIJ) Vol.3, No.2, April 2012.
[9] Wonjun Hwang, KyungshikRoh and Junmo Kim, “Markov Network-based Unified Classifier for Face
Identification”, ICCV 2013.
[10] Patrick Grother and Mei Ngan, “Face Recognition Vendor Test (FRVT)”, Performance of Face Identification
Algorithms, NIST Interagency Report 8009, May 2014.

ABOUT AUTHORS
1
Dr. R. Satya Prasad received Ph.D. degree in Computer Science in the faculty of Engineering in 2007
from AcharyaNagarjuna University, Andhra Pradesh. He received gold medal from AcharyaNagarjuna
University for his out standing performance in Masters Degree. He is currently working as Associate
Professor and H.O.D, in the Department of Computer Science & Engineering, AcharyaNagarjuna
University. His current research is focused on Software Engineering, Software reliability. He has published
several papers in National & International Journals.
2
Muzhir Shaban Al-Ani has received Ph. D. in Computer & Communication Engineering Technology,
ETSII, Valladolid University, Spain, 1994. Assistant of Dean at Al-Anbar Technical Institute (1985). Head
of Electrical Department at Al-Anbar Technical Institute, Iraq (1985-1988), Head of Computer and
Software Engineering Department at Al-Mustansyria University, Iraq (1997-2001), Dean of Computer
Science (CS) & Information System (IS) faculty at University of Technology, Iraq (2001-2003). He joined
in 15 September 2003 Electrical and Computer Engineering Department, College of Engineering, Applied
Science University, Amman, Jordan, as Associated Professor. He joined in 15 September 2005
Management Information System Department, Amman Arab University, Amman, Jordan, as Associated
Professor, then he joined computer science department in 15 September 2008 at the same university. He
joined in August 2009 College of Computer Science, Al-Anbar University, Al-Anbar, Iraq, as Professor.
3
Salwa Mohammed Nejres has received in B.Sc. in Computer Science from University of Mustansiriya,
Department of Computer Sciences, Iraq (2001-2002). She completed her M.Sc. in Computer Science
Department at AL- Anbar University in the field of data mining (2009-2010). She is currently a Ph.D.
student in computer Science Department of AcharyaNagarjuna University (ANU),Nagarjunanagar, India,
ANU College of Engineering & Technology.

© 2015, IJARCSSE All Rights Reserved Page | 136

View publication stats