International Conference on Computing, Communication and Automation (ICCCA2017)

A Study on Face Recognition Techniques with Age

and Gender Classification
Sandeep Kumar Sukhwinder Singh Jagdish Kumar
Department of Electronics and Department of Electronics and Department of Electrical
Communication Engineering Communication Engineering Engineering
PEC University of Technology, PEC University of Technology, PEC University of Technology,
Chandigarh-160012, India Chandigarh-160012, India Chandigarh-160012, India
sandeepkumar.phdece15@pec.edu.in sukhwindersingh@pec.ac.in jagdishkumar@pec.ac.in

Abstract- Nowadays research has explored to extracting
auxiliary information from various biometric techniques such as
fingerprints, face, iris, palm, voice etc. This information contains
some features like gender, age, beard, mustache, scars, height,
hair, skin color, glasses, weight, facial marks, tattoos etc. All this
information contributes more and more to identification. The
major changes that come across face recognition are to find age
& gender of the person. This paper contributes a significant
survey of various face recognition techniques for finding the age
and gender. The existing techniques are discussed based on their
performances. This paper also provides future directions for
further research.
Keywords- Biometrics, Age, Face Recognition, Gender.
I. INTRODUCTION
Biometrics is the unique measurable characteristics of
automatically recognizing an individual identification based
on their physical and behavioral characteristics [1]. The
Physiological parameters are physique of the body such as
fingerprint, face, palm, iris and DNA [2]. On the other hand
behavioral involves the behavior of a person such as signature,
keystrokes, and voice.
In the last 51 years, the face recognition system has been
researched as a low-cost tool and is reliable in the diverse
fields such as forensic, commercial, health-care,
entertainment, government, traveling and immigration etc [3].
Nowadays the biometric driven systems are proliferating
exponentially all over the world. The biometrics market was
$4 hundred million in the year 2000 which grew to $5 billion
in the year 2011. It is expected that the biometrics business
would grow up to $23 billion in the year of 2019 [10]. Due to
their intrusive property, the success of some biometrics
systems (i.e. fingerprint, palm, and iris) depends on user
cooperation but face recognition systems are non-intrusive as
it doesn’t require the physical interaction of users to be
identified, once the input is acquired [5]. One more important
characteristic is Passive Identification which means the person
is not required to be subjected to physical verification [6]. This
is why personal authentication face recognition is considered
as the friendly among all biometrics. The face biometric
system can identify various attributes from the image such as
gender, age, beard, mustache, scars, height, hair, skin color,
glasses, weight, facial marks, tattoos etc as shown in Fig-1.
From these attributes, a biometric system can extract some
information from the data and compares this information with
the templates in the database to determine an identity.
Face
Gender Contact Lens Beard
AGE Glasses Moustache
Hair Cap Makeup
Skin Accessories Tattoos
Scars Facial Marks Moles
Fig-1: Auxiliary information from the face
In 1960 Woody (et al.) gave the first semi-automated facial
recognition technique. This technique required some features
such as mouth, nose, eyes and nose on the image [2][3]. The
year 2001 onwards, the biometric techniques proliferated
rapidly indication of which are the increased number of
publication of research papers in this field (refer Fig-2). A
detailed literature survey was carried out by the authors of this
paper to justify the constantly increasing scientific interest in
face recognition biometric technique. The authors analyzed
the publication of the last 51 years related to the face through
the database extracted from the well known and qualified
sources of Scopus [4]. The mentioned database includes
enough information for our analysis hence, it would be
acceptable to the research and scientific community. The
analysis was carried out by applying the keyword ‘face
recognition’. The face recognition database has been obtained
from the different type of publications, the broad
classifications of which are shown in Fig-3. Moreover, the
increased publications of research papers in the past decade
are the testimony of the importance of face recognition
techniques. The analysis of Fig-3 reveals that the number of
books and autographs published in the field of face
recognition is a small percentage compared to the research
papers published during the past 15 years. However, during

ISBN: 978-1-5090-6471-7/17/$31.00 ©2017 IEEE 1001

Authorized licensed use limited to: VIT University. Downloaded on July 30,2022 at 10:56:59 UTC from IEEE Xplore. Restrictions apply.
 International Conference on Computing, Communication and Automation (ICCCA2017)

Fig-2: Face Recognition related publications for the past 51 years

the same period publications of research papers have been
more productive. The stated analysis indicates the heavy
leaning of the research in the field of face recognition and
thus, the highest evolution in this field so far. Such a high
degree of research activities in the field of face recognition is
creating high pre-knowledge that must favor the discovery and
development of the next generation frameworks in the face
recognition and applications.
The various types of challenges that are faced during face
detection are described below:
A. Pose
The most challenging situation is that the human face
varies with respect to the relative camera-face pose (45
degrees, profile, frontal and upside down).
B. Facial Expression
The facial expression such as anger, fear, disgust,
happiness, sadness and surprise is most influential
temperaments for human beings to communicate their
feelings.
C. Illumination
Illumination is a major challenge during face recognition.
This factor is related to the lumn value and angle of the light.
D. Occlusion
Occlusion is one of the typical challenges during face
recognition because sometimes the face is partially covered
and occluded by others objects.
E. Imaging Condition

Fig-3: Face related publications for the past 51 years for different Documents
II. CHALLENGES of FACE RECOGNITION
Most of the applications such as computer security, human
crowd surveillance, face processing, AI driven applications
content-based image retrieval and video surveillance etc.
require face detection for identification and verification of the
enrolled users [7]. The major challenges which any face
recognition techniques face are the skin color segmentation
and the facial segmentation accuracy [8-9]. The facial
segmentation accuracy depends on the pose, noise, lighting
conditions and distance between the object and the camera.
During the face image capture, some factors such as
different illumination conditions and camera characteristic
(lenses, sensor response) affect the face recognition accuracy.
F. Different Facial Features
Different type of facial features such as glasses, beard,
hair, mustache, scars, moles, tattoos, skin colors and makeup
affect the face recognition accuracy.
G. Face Size
This factor poses another typical challenge because face
size can vary a lot from a person to another person. Not only
different people have different sized faces but the face closer

1002

Authorized licensed use limited to: VIT University. Downloaded on July 30,2022 at 10:56:59 UTC from IEEE Xplore. Restrictions apply.
 International Conference on Computing, Communication and Automation (ICCCA2017)
to the camera and far away from the camera also pose a
challenge.
H. Rotation of Optical axis of the camera
This factor depends on the nature of the images i.e. face
images vary at different camera rotations about its optical axis.
III. TYPES of FACE RECOGNITION
Face recognition is the sub-area of pattern recognition (a) (b)
research and technology. Overview of face recognition system
is shown in Fig-4. Firstly, the input image is taken from the
standard camera that are known as input image [3]. The
second step involves pre-processing of the image to improve
the image quality and to reduce the noise in the image. Next
phase is face segmentation where face part is cropped from the
human body and background of the image. In the next phase,
feature extraction is done after segmenting the input image to
a very good level so that relevant features are identified that
can help in distinguishing that person to other people. In the (c) (d)
last phase, a template is generated for enrollment and Fig -5: (a) Original Image, (b) Skin Color Binary Image, (c) Skin Color
matching purpose. Finally, a matching is done at the biometric Mark Area, (d) Image verified by face length-breadth ratio [14]
system for identification of the authenticated person, if there is
a match then the output will come in the form of user accepted C. Template-based methods
otherwise user rejected [2][7]. Face recognition systems can Template-based methods are sensitive to pose, scale and
be divided into different categories: shape variation of the human body. Deformable template
A. Knowledge-based methods methods have been proposed to deal with such variations of
pose, scale, and shape of the body. Template-based methods
The knowledge-based techniques are based on the using the elastic models include shape parameters as well as
geometry of the face and arrangement of the facial features intensity information of facial features.
[11]. These knowledge-based methods describe the shape,
size, and texture. Some methods describe few other
characteristics of facial features such as head, eyebrows, eyes,
nose and chin [12]. The major problem of these techniques is
that they do not perform well because of different types of
pose or head orientations as shown in my implementation
results of the V-J algorithm in Fig-4 [13].

Fig-6: A 14x16 pixel ratio template [8]

Fig-4: Face Segmentation Results obtained on CMU dataset images
B. Feature invariant approaches
The main aim of these techniques is to find structural
features of the human face even with lighting conditions
varying. Different types of structural features such as facial
local features, skin color, shape, and texture are used [14, 15].
These methods are very sensitive to illumination, occlusion,
the existence of skin color regions, and adjacent faces as
shown in Fig-5.
D. Appearance-based methods
The appearance-based methods used for face detection are
Eigenfaces, Linear Discriminant Analysis, Neural Networks,
Support Vector Machine, and Hidden Markov Models. With
the help of these methods, the whole image is scanned and
image regions are identified as a face or nonface. During
template matching, appearance-based methods will come in
the picture.
The first main step of face recognition system is facing
segmentation and comparison of various types of face
detection techniques as shown in Table I. According to
literature survey, face detection techniques have low accuracy
so there is a scope of improvement in term of accuracy. The
second main step of face recognition system is the feature
extraction and according to Table II performance is not
optimum so there is a scope of further improvement in feature
extraction techniques. Various types of face databases which

1003

Authorized licensed use limited to: VIT University. Downloaded on July 30,2022 at 10:56:59 UTC from IEEE Xplore. Restrictions apply.
 International Conference on Computing, Communication and Automation (ICCCA2017)
are easily available for research community on the internet and IV. AGE CLASSIFICATION
some well-known face database are shown in Table III. Face recognition systems are essential for real-time
TABLE I: COMPARISON OF EXISTING TECHNIQUES OF FACE applications such as for identification of the missing children
DETECTION and passport verification because there is the significant age
Ref Segmentation Dataset Performance difference between investigating and gallery images [26]. One
Techniques more practical application in which age is a condition for
[12] RGB Colour Space Self-prepared Detection Rate = 80% access to a product is alcohol or tobacco. Table IV represents
120 Images the comparison of various techniques to find out the ages of
[16] YcbCr + RGB + FRGC 302 Detection Rate = 82.7%
Canny Edge Images
[17] Skin Colour Self-prepared Detection Rate = 88.9%
[18] Adaboost & SVM MIT + CMU Detection Rate = 94.5%
(2500 Images)
[19] RGB-H-CbCr Self-prepared Detection Rate = 90%
TABLE II: COMPARISON OF EXISTING TECHNIQUES OF FACE
FEATURE EXTRACTION
Ref Segmentation Feature Dataset Performance
Techniques Extraction
Haar Features LBP CK+ and Accuracy=89.64%
[20] and Adaboost JAFFE
Adaboost LBP and FDDB and Accuracy=91%
[21] MCT MIT +
CMU
Skin Color ANN LFW and Accuracy= 89.5%
[22] PEAL
Fig-7: Age-related publications for the past 10 years
Viola-Jones SVM Self- Training time
[23] prepared period 60% different categories. Two important factors play a vital role in
300 Images increases the real life. Firstly, accumulated data suggest that age
Hough SVM AR database FR rate increased
[24] Transform by 7.7%
estimation faces can be quite accurate, but there is the scope
for further improvement because age factor is sensitive and
LBP: Local Binary Pattern, ANN: Artificial Neural Network, SVM: Support depends on the basis of group membership [27]. Secondly, it
Vector Machine, MCT: Modified Census Transform
is proved that human face aging depends on ethnicity and
genders. This analysis gives right directions for further
TABLE III: COMPARISON OF DIFFERENT FACE DATABASE [25]
research to identify the ages from the images.
Database Description
TABLE IV: EXISTING INTRODUCTORY OVERVIEWS ON AGE
AT & T 40 people with 10 images of each (different lighting
ESTIMATION TECHNIQUES
Database conditions).
AR Database 4,000 color images of 70 men’s and 56 women’s.
CAS-PEAL Face 99,594 images of 1040 people are in different Pose, Ref Feature Database Accuracy
Database Expression, Accessory, and Lighting conditions. Extraction
CMU Multi-PIE 750,000 images of 337 people. [31] SVM FG-NET 95.6%
CK 486 images of 97 people’s MORPH
FERET 1000 people of images [32] PCA+USA FG-NET 94.87%
Kinect Face 52 people in different lighting and occlusion [33] Deep NN eWIT 65.8%
Database conditions. [34] NTCA+LBP FG-NET 83.8%
Georgia Tech 50 people of images. MORPH
Indian Movie 34512 images of 100 Indian actors are in different age, [35] PCA/SVM CACD 94.2%
database pose, gender, expression, and occlusion. MORPH
JAFFE 213 images of 7 facial expressions each female [36] Gabor/HOG WhoIsIt 80%
Labeled 8,500 faces (taken from Wikipedia). FG-Net
Wikipedia faces [37] KDCV / NN FG-NET 93%
LDHF Database 100 people’s images at different distances of 60m, [38] SVM LFW 89%
100m, and 150m from the subject’s. [39] AAM FG-NET 95%
MIT-CBCL 200 images are in different illumination, pose, and [40] GOP+SVM Passport 70%
database complex background. [41] GB FG-NET 82.7%
YouTube 604 images of 151 subjects [42] RMIR MORFH MAE=8.6
MORPH 55,134 images of 13,000 people’s. This database [43] DML FG-NET 84%
Database describes gender, date of birth, and date of acquisition.
[44] SSE FG-NET MAE=5.21
3D face 1149 of the facial color of 105 adults.
[45] AMF YGA MAE=8(M), 7.8(F)
Oulu Face 125 different faces are in different illuminant
Database conditions. SVM: Support Vector Machine, PCA: Principal Component Analysis,
Yale face 165 greyscale images of 15 individuals - 11 images per LBP: Local Binary Pattern, NN: Neural Network, HOG: Histogram of
Database subject. Oriented Gradient, AAM: Active Appearance Model
YouTube Faces 3,425 videos of 1,595 different people’s.
The PUT Face 9971 images of 100 people’s.

1004

Authorized licensed use limited to: VIT University. Downloaded on July 30,2022 at 10:56:59 UTC from IEEE Xplore. Restrictions apply.
 International Conference on Computing, Communication and Automation (ICCCA2017)
V. GENDER CLASSIFICATION the field of face recognition. During face recognition some
Gender classification is an easy task for humans to identify well-known problems such as pose, facial expression,
illumination, occlusion, different facial features etc. have
a person according to his or her face but it’s a very
attained a lot of attention in the research community of
challenging task for computers [28]. Last 10 years of gender computer vision and pattern recognition. Various types of
classification for different databases are shown in Fig. 8. This techniques have been proposed to compensate for all these
analysis gives fruitful directions for further research in the challenges but still, there are some unsolved challenges, so
field of gender classification [29]. there is a scope of optimization. All these analyses will give a
right direction to the researcher in future to resolve the
unsolved challenges.
REFERENCES
[1] Zhang, Xiaozheng, and Yongsheng Gao. "Face recognition across pose:
A review" Pattern Recognition, vol 42, no. 11, pp. 2876-2896, 2009.
[2] Tolba, A. S., A. H. El-Baz, and A. A. El-Harby. "Face recognition: A
literature review." International Journal of Signal Processing, vol 2, no.
2, pp. 88-103, 2006.
[3] Dantcheva, Antitza, Petros Elia, and Arun Ross. "What else does your
biometric data reveal? A survey on soft biometrics." IEEE Transactions
on Information Forensics and Security, vol 11, no. 3, pp. 441-467, 2016.
[4] Papakostas, George A. "Over 50 Years of Image Moments and Moment
Invariants." Moments and Moment Invariants-Theory and Applications,
pp. 3-32, 2014.
Fig. 8: Gender-related publications for the past 10 years
[5] Zafeiriou, Stefanos, Cha Zhang, and Zhengyou Zhang. "A survey on
Gender classification has gained a lot of interest in the face detection in the wild: past, present and future." Computer Vision
and Image Understanding, vol. 138 pp. 1-24, 2015.
research community because of its wide application such as
man-machine communication [30], security, law enforcement, [6] Jin, Jing, Bin Xu, Xiaoliang Liu, Yuanqing Wang, Liqun Cao, Lei Han,
Biye Zhou, and Minggao Li. "A face detection and location method
demographics studies, education, and telecommunication, etc. based on Feature Binding." Signal Processing: Image
Gender classification is a useful preprocessing step for face Communication, vol. 36, pp. 179-189, 2015.
recognition. The face recognition has been explored in a large [7] Hatem, Hiyam, Zou Beiji, and Raed Majeed. "A Survey of Feature Base
manner by many researchers but very few works have been Methods for Human Face Detection." International Journal of Control
explored in the case of gender classification [28]. The face and Automation, vol. 8, no. 5, pp. 61-78, 2015.
image is used for classifying the gender, so the gender [8] Rizvi, Qaim Mehdi, Bal Gopal Agarwal, and Rizwan Beg. "A Review of
classification process can make face recognition twice as fast Face Detection Methods.", 2011.
by reducing the search time for recognizing the person. Table [9] Yang, Ming-Hsuan, David J. Kriegman, and Narendra Ahuja. "Detecting
faces in images: A survey." IEEE Transactions on pattern analysis and
V represents the comparison of various techniques for machine intelligence, vol. 24, no. 1, pp. 34-58, 2002.
identification to the gender.
[10] https://www.bostonglobe.com/ideas/2014/11/23/facial-recognition-
TABLE V: EXISTING INTRODUCTORY OVERVIEWS ON GENDER technology-goes-way-back/CkWaxzozvFcve Q7kvdLHGI/story.html
[11] Kouzani, Abbas Z., Fangpo He, and Karl Sammut. "Commonsense
ESTIMATION TECHNIQUES
knowledge-based face detection." IEEE International Conference on
Ref. Feature Classifiers Database Accuracy Intelligent Engineering Systems ( INES'97), pp. 215-220, 1997.
Extraction [12] Devadethan, S., Geevarghese Titus, and S. Purushothaman. "Face
detection and facial feature extraction based on a fusion of knowledge
[46] LBP NN FERET 80.2% based method and morphological image processing." IEEE Annual
[47] PCA LDA FERET 85% International Conference on Emerging Research Areas: Magnetics,
[48] LBP and WLD Nearest FERET 98.82% Machines, and Drives (AICERA/iCMMD), pp. 1-5, 2014.
Neighbor
[13] Sun, Wei, Weigong Zhang, Xiaorui Zhang, Gang Chen, and Chengxu
[49] PCA SVM & K-NN Self-prepared 93% Lv. "Multi-feature driver face detection based on area coincidence
[50] PCA CDLA FERET 87.44% degree and prior knowledge." The 4th IEEE Conference on Industrial
[51] Adaboost Fusion FRGCv2 86% Electronics and Applications, pp. 222-225, 2009.
[52] PCA Euclidean FERET 82% [14] Fei, Zhao, and Qiao Qiang. "Face detection based on rectangular
[53] PCA LDA FRGC 55.47% knowledge rule and face structure." The First International Conference
[54] PCA SVM Self-prepared 93.33% on Information Science and Engineering, 2009.
[55] LBP Adaboost Private 96.32%
[15] Yadav, Shalini, and Neeta Nain. "Fast Face Detection Based on Skin
[56] LBP Adaboost FERET 95.75% Segmentation and Facial Features." The 11th International Conference
[57] PCA NN Private 88.7% on Signal-Image Technology & Internet-Based Systems (SITIS), pp.
[58] ICA LDA FERET 99.3% 663-668, 2015.
LBP: Local Binary Pattern, PCA: Principal Component Analysis, NN: [16] Ghimire, Deepak, and Joonwhoan Lee. "A robust face detection method
Neural Network, LDA: Linear Discriminative Analysis, SVM: Support based on skin color and edges." Journal of Information Processing
Vector Machine Systems, vol. 9, no. 1, pp. 141-156, 2013.
[17] Liu, Qiong, and Guang-zheng Peng. "A robust skin color-based face
VI. CONCLUSION detection algorithm." The 2nd International Asia Conference
on Informatics in Control, Automation and Robotics (CAR), pp. 525-
This paper presents a comprehensive survey of face 528, 2010.
recognition and various challenges in the last 51 years. This
literature analysis showed continuously increasing interest in

1005

Authorized licensed use limited to: VIT University. Downloaded on July 30,2022 at 10:56:59 UTC from IEEE Xplore. Restrictions apply.
 International Conference on Computing, Communication and Automation (ICCCA2017)
[18] Valiollahzadeh, Seyyed Majid, Abolghasem Sayadiyan, and Mohammad
Nazari. "Face detection using adaboosted SVM-Based component
classifier." arXiv preprint arXiv:0812.2575, 2008.
[19] Bin Abdul Rahman, Nusirwan Anwar, Kit Chong Wei, and John See.
"RGB-h-cbcr skin color model for human face detection." Faculty of
Information Technology, Multimedia University, 2007.
[20] Happy, S. L., and Aurobinda Routray. "Automatic facial expression
recognition using features of salient facial patches." IEEE transactions
on Affective Computing, vol. 6, no. 1, pp. 1-12, 2015.
[21] Jeong, Kyung Joong, Jaesik Choi, and Gil-Jin Jang. "Semi-local
structure patterns for robust face detection." IEEE Signal Processing
Letters, vol. 22, no. 9, pp. 1400-1403, 2015.
[22] Ye, Xueyi, Xueting Chen, Huahua Chen, Yafeng Gu, and Qiuyun Lv.
"Deep learning network for face detection." The 16th International
Conference on Communication Technology (ICCT), pp. 504-509, 2015.
[23] Mingxing, Jia, Du Junqiang, Cheng Tao, Yang Ning, Jiang Yi, and
Zhang Zhen. "An improved detection algorithm of the face with
combining AdaBoost and SVM." The 25th Chinese Control and
Decision Conference (CCDC), pp. 2459-2463, 2013.
[24] Kawulok, Michal, and Janusz Szymanek. "Precise multi-level face
detector for advanced analysis of facial images." IET image processing,
vol. 6, no. 2, pp. 95-103, 2012.
[25] https://www.kairos.com/blog/60-facial-recognition-databases
[26] Juefei-Xu, Felix, Khoa Luu, Marios Savvides, Tien D. Bui, and Ching
Y. Suen. "Investigating age invariant face recognition based on
periocular biometrics." The International Joint Conference on
Biometrics (IJCB), pp. 1-7, 2011.
[27] Rothe, Rasmus, Radu Timofte, and Luc Van Gool. "DEX: Deep
Expectation of apparent age from a single image." IEEE International
Conference on Computer Vision Workshops, pp. 10-15, 2015.
[28] Bissoon, Terishka, and Serestina Viriri. "Gender classification using
face recognition." The International Conference on Adaptive Science
and Technology, pp. 1-4, 2013.
[29] Yang, Zhiguang, Ming Li, and Haizhou Ai. "An experimental study on
automatic face gender classification." In 18th International Conference
on Pattern Recognition (ICPR'06), pp. 1099-1102, 2006.
[30] Sun, Zehang, George Bebis, Xiaojing Yuan, and Sushil J. Louis.
"Genetic feature subset selection for gender classification: A comparison
study." In Sixth IEEE Workshop on Applications of Computer Vision,
(WACV 2002), pp. 165-170, 2002.
[31] Wang, Shengzheng, Dacheng Tao, and Jie Yang. "Relative Attribute
SVM+ Learning for Age Estimation." IEEE transactions on cybernetics,
vol. 46, no. 3, pp. 827-839, 2016.
[32] Li, Zhifeng, Dihong Gong, Xuelong Li, and Dacheng Tao. "Aging Face
Recognition: A Hierarchical Learning Model Based on Local Patterns
Selection." IEEE Transactions on Image Processing, vol. 25, no. 5 pp.
2146-2154, 2016.
[33] Nagpal, Shruti, Maneet Singh, Richa Singh, and Mayank Vatsa.
"Regularized Deep Learning for Face Recognition With Weight
Variations." IEEE Access 3, pp. 3010-3018, 2015.
[34] Bouchaffra, Djamel. "Nonlinear topological component analysis:
application to age-invariant face recognition." IEEE transactions on
neural networks and learning systems, vol. 26, no. 7, pp. 1375-1387,
2015.
[35] Chen, Bor-Chun, Chu-Song Chen, and Winston H. Hsu. "Face
recognition and retrieval using cross-age reference coding with cross-
age celebrity dataset." IEEE Transactions on Multimedia, vol. 17, no. 6
pp. 804-815, 2015.
[36] Singh, Maneet, Shruti Nagpal, Richa Singh, and Mayank Vatsa. "On
recognizing face images with weight and age variations." IEEE Access 2
pp. 822-830, 2014.
[37] Ali, Amal Seralkhatem Osman, Vijanth Sagayan, Aamir Malik Saeed,
Hassan Ameen, and Azrina Aziz. "Age-invariant face recognition
system using combined shape and texture features." IET Biometrics, vol.
4, no. 2, pp. 98-115, 2015.
[38] Eidinger, Eran, Roee Enbar, and Tal Hassner. "Age and gender
estimation of unfiltered faces." IEEE Transactions on Information
Forensics and Security, vol. 9, no. 12, pp. 2170-2179, 2014.
[39] Wang, Yunhong, Zhaoxiang Zhang, Weixin Li, and Fangyuan Jiang.
"Combining tensor space analysis and active appearance models for
1006
Authorized licensed use limited to: VIT University. Downloaded on July 30,2022 at 10:56:59 UTC from IEEE Xplore. Restrictions apply.
aging effect simulation on face images." IEEE Transactions on Systems,
Man, and Cybernetics, Part B (Cybernetics), vol. 42, no. 4, pp. 1107-
1118, 2012.
[40] Ling, Haibin, Stefano Soatto, Narayanan Ramanathan, and David W.
Jacobs. "Face verification across age progression using discriminative
methods."IEEE Transactions on Information Forensics and security, vol.
5, no. 1, pp. 82-91, 2010.
[41] J. Suo, S.-C. Zhu, S. Shan, and X. Chen, “A compositional and dynamic
model for face aging,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 32,
no. 3, pp. 385–401, 2010.
[42] B. Ni, Z. Song, and S. Yan, “Web image mining towards universal age
estimator,” in Proc. 17th ACM Int. Conf. Multimedia, pp. 85–94, 2009.
[43] B. Xiao, X. Yang, Y. Xu, and H. Zha, “Learning distance metric for
regression by semidefinite programming with application to human age
estimation,” in Proc. 17th ACM Int. Conf. Multimedia, 2009, pp. 451–
460, 2009.
[44] S. Yan, H. Wang, Y. Fu, J. Yan, X. Tang, and T. S. Huang,
“Synchronized submanifold embedding for person-independent pose
estimation and beyond,” IEEE Trans. Image Process., vol. 18, no. 1, pp.
202–210, 2009.
[45] X. Zhuang, X. Zhou, M. Hasegawa-Johnson, and T. Huang, “Face age
estimation using patch-based hidden Markov model supervectors,” In
Proc. 19th Int. Conf. Pattern Recognit., pp. 1–4, 2008.
[46] Amilia, Sindi, Mahmud Dwi Sulistiyo, and Retno Novi Dayawati. "Face
image-based gender recognition using the complex-valued neural
network." The 3rd International Conference on Information and
Communication Technology (ICoICT), pp. 201-206, 2015.
[47] Bissoon, Terishka, and Serestina Viriri. "Gender classification using
face recognition." The International Conference on Adaptive Science
and Technology, pp. 1-4, 2013.
[48] Alamri, Taghreed, Muhammad Hussain, Hatim Aboalsamh, Ghulam
Muhammad, George Bebis, and Anwar M. Mirza. "Category Specific
Face Recognition Based On Gender." The International Conference on
Information Science and Applications (ICISA), pp. 1-4, 2013.
[49] Sakarkaya, Mutlu, Fahrettin Yanbol, and Zeyneb Kurt. "Comparison of
several classification algorithms for gender recognition from face
images." The IEEE 16th International Conference on Intelligent
Engineering Systems (INES), pp. 97-101, 2012.
[50] Chen, Duo, Jun Cheng, and Dacheng Tao. "Clustering-based
discriminative locality alignment for face gender recognition." The IEEE
International Conference on Intelligent Robots and Systems, pp. 4156-
1461, 2012.
[51] Ballihi, Lahoucine, Boulbaba Ben Amor, Mohamed Daoudi, Anuj
Srivastava, and Driss Aboutajdine. "Boosting 3-D-geometric features for
efficient face recognition and gender classification." IEEE Transactions
on Information Forensics and Security, vol. 7, no. 6, pp. 1766-1779,
2012.
[52] Akbari, Rohollah, and Saeed Mozaffari. "Performance enhancement of
PCA-based face recognition system via gender classification method."
The 6th Iranian Conference on Machine Vision and Image Processing,
pp. 1-6, 2010.
[53] Hwang, Wonjun, Haibing Ren, Hyunwoo Kim, Seok-Cheol Kee, and
Junmo Kim. "Face recognition using gender information." The 16th
IEEE International Conference on Image Processing (ICIP), pp. 4129-
4132, 2009.
[54] Zhang, De, and Yun-Hong Wang. "Gender recognition based on fusion
of face and gait information." The International Conference on Machine
Learning and Cybernetics, pp. 62-67, 2008.
[55] Z. Yang and H. Ai, “Demographic classification with local binary
patterns,” In Proc. IAPR Int. Conf. Biometrics, pp. 464–473, 2007.
[56] N. Sun, W. Zheng, C. Sun, C. Zou, and L. Zhao, “Gender classification
based on boosting local binary pattern,” In Proc. 3rd Int. Symp. Adv.
Neural Netw., pp. 194–201, 2006.
[57] A. Khan, A. Majid, and A. M. Mirza, “Combination and optimization of
classifiers in gender classification using genetic programming,” Int. J.
Knowl.-Based Intell. Eng. Syst., vol. 9, no. 1, pp. 1–11, 2005.
[58] A. Jain and J. Huang, “Integrating independent components and linear
discriminant analysis for gender classification,” In Proc. 6th IEEE Int.
Conf. Autom. Face Gesture Recognit., pp. 159–163, 2004.