Conference PaperPDF Available

İris Görüntülerinden Derin Öğrenme ile Cinsiyet Sınıflandırma

  • December 2018
  • Conference: World Symposium of Multidisciplinary Research (WOSMUR2018)
  • At: Mersin, Turkey
  • Volume: Vol.2 No.2, pp.25-31
Authors:
Tuğba AÇIL
Tuğba AÇIL
Tuğba AÇIL
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Yakup Kutlu at Iskenderun Technical University, Hatay, Turkey
Yakup Kutlu
  • Iskenderun Technical University, Hatay, Turkey
Gokhan Altan at Iskenderun Technical University
Gokhan Altan
  • Iskenderun Technical University
Download full-text PDF
Read full-text
Download citation
Content uploaded by Gokhan Altan
Author content
All content in this area was uploaded by Gokhan Altan on Jan 09, 2019
Content may be subject to copyright.
0
1. International Mersin Symposium
SYMPOSIUM FULL TEXT BOOK
2 / VOLUME 2
1
1. International Mersin Symposium
SYMPOSIUM FULL TEXT BOOK
2 / VOLUME 2
Prof. Dr. D. Ali ARSLAN
Prof. Dr. D. Ali ARSLAN
Mizanpaj- Prof. Dr. D. Ali ARSLAN
Mer Ak
2018 Mersin
ISBN: 978-605-89406-9-7
Adres: esi, 34. Cadde, Nisa 1 Evleri, No: 35, 6/12,
Tel: 0532 270 81 45 / 0553 666 06 06
Not
15
221
-
Zizyphus jujuba Mill.) 239
Hakan KELES
246
Halil KUMBUR-
255
Halil KUMBUR-
Mut - Haziran-
262
On the Asym
ptotic Formulas for Eigenfunctions of A Quadratic Differantial
Pencil Problem
287
Hamza MENKEN- - Khanlar R. MAMEDOV
295
- EKER- -Ebru KAFKAS
Chemical Composition of Different Pomegranate Varieties 301
- Ebru KAFKAS
Recent Advances on Postharvest Technologies of Berries 308
- Ebru KAFKAS
-
312
322
331
- - Simge YILMAZ
Otomikoz Etkeni Candida 342
Hafize SAV
347
- Orhan ERDEN
356
-
- 368
Mu
379
25
- Yakup KUTLU-
-
32
25
i
Yakup KUTLU
nsiyet tespiti
a cinsiyet tespit sistemi
1
Anahtar Kelimeler:
Gender Classification with Deep Learning from Iris Images
Abstract: The gender detection system has a wide range of applications. For example, if
you search the database for a searched person's gender, it will be easier to search and
shorten the search time Particularly due to the increasing number of population, it is very
important to reduce the data to be searched by means of gender determination. In the case
of security applications requiring gender-based access control, the gender determination
system is highly demanded in the creation of marketing strategies that address only a
1
tugbaacil.mfbe16@iste.edu.tr
yakup.kutlu@iste.edu.tr
gokhan.altan@iste.edu.tr
26
specific gender group. Biometric properties such as fingerprint, face, voice, signature
beat, iris are used for person identification and verification. However, due to the unique
structure of iris, it is thought to be a more reliable system than other biometric properties.
In this study, gender prediction was made by using iris structure. The eye images used for
gender estimation were taken from ND_GFI database. 750 women and 750 men, a total
of 1500 images were applied on the application. These iris images were classified by deep
learning. 1000 data was used for the training and 500 for the test. With at the stage of
training 80% and in the test phase 70% success rate, gender estimation could be made.
Key Words: Iris, Gender Classification, Deep Learning
1.
renklerde ve desende olup
(
ve Akbulut 2013).
olarak t 2009).
Bunlardan birisi
(Tapia ve Aravena 2017).
parmak izi (
( Huang,
Jia ve Wu 2009) (Guo, Lin, ve Nguyen 2010; Jain, Huang ve Fang 2005; Stawska ve
Milczarski 2017), ses (Kotti ve Kotropoulos 2008), kalp sesi 2015),
iris (Bansal, Agarwal ve Sharma 2014; Kuehlkamp, Becker ve Bowyer 2017; Thomas,
Chawla, Bowyer ve Flynn 2007)
irisin
iris tarama cinsiyet
27
ndedir.
Atul Bansal ve ark. (Bansal, Agarwal ve Sharma 2014)
Juan E. Tapia ve ark. (Tapia, Perez ve Bowyer 2016)
kulla
. Yaman Akbulut ve ark.
(Akbulu 2017)
Adience .
mevcuttur
Alanlar- (YAA-
Amrolkar ve Tugave
2015) en ND-
Faz Kuantizasyonu ve Generalized Region Assigned
.
2. Materyal ve Metot
ve Bowyer 2016)..
28
2.2.
i
Bu
Bu nedenle b
rimi .
22].
640x320
ve gri tonludur. katman
olarak bilinen r
D
29
.
sonraki konvol
.
2.4. Performan
Burada
tahmin
durumu, olarak
Hassasiyet = (
1)
(2
(3
=
(4
ver
30
ksek
.
deep learning, In Artificial Intelligence and Data Processing Symposium (IDAP),
International (pp. 1-4). IEEE.)
Amrolkar, K. & Tugave, A.S. (2015, Gender Classification from Iris Using Machine
Learning Techniques)
Bansal, A., Agarwal, R. & Sharma, R.K. (2014, Predicting Gender Using Iris Images,
Research Journal of Recent Sciences 3(4):20 26.)
Journal of the Faculty of Engineering
and Architecture of Gazi University 29(1):201 7.)
lysis based on
fingerprint ridge density, In Signal Processing and Communications Applications
Conference (SIU), (pp. 1-4). IEEE.)
Chang, C. Y. & Wu, T. H. (2010, Using gait information for gender recognition,
In Intelligent Systems Design and Applications (ISDA), International Conference on (pp.
1388-1393). IEEE.)
5. , 13.)
with heart sound, In Signal
Processing and Communications Applications Conference (SIU), (pp. 2362-2365), IEEE.)
Guo, J. M., Lin, C. C., & Nguyen, H. S. (2010, Face gender recognition using improved
appearance-based average face difference and support vector machine, In System Science
and Engineering (ICSSE), International Conference on (pp. 637-640). IEEE.
31
, 6(3), 85-104.)
Jain, A., Huang, J., & Fang, S. (2005, Gender identification using frontal facial images,
In Multimedia and Expo. ICME. IEEE International Conference on IEEE.
Kotti, M., & Kotropoulos, C. (2008, Gender classification in two emotional speech
databases, In Pattern Recognition, ICPR 19th International Conference on(pp. 1-4). IEEE.)
Kuehlkamp, A., Becker, B. & Bowyer, K. (2017, Gender-from-Iris or Gender -from-
Mascara?, IEEE Winter Conference on Applications of Computer Vision, WACV 1151
1159.)
Stawska, Z. & Milczarski P. (2017, Support Vector Machine in Gender Recognition,
Information System in Management 6(4):318-329.)
, 9,
683-689.)
Tapia, J.E. & Aravena, C. (2017, Gender classification from NIR iris images using deep
learning, In Deep Learning for Biometrics(pp. 219-239). Springer, Cham.)
Tapia, J. E., Perez, C. A., & Bowyer, K. W. (2016, Gender classification from the same iris
code used for recognition. IEEE Transactions on Information Forensics and Security, 11(8),
1760-1770.)
Thomas, V., Chawla, N.V., Bowyer, K.W. & Flynn, P.J. (2007, Learning to Predict Gender
from Iris Images, IEEE Conference on Biometrics: Theory, Applications and Systems,
, First IEEE International Conference on (pp. 1-5).)
In Signal Processing and Communications Applications Conference (SIU), (pp. 1-4). IEEE.)
Yu, S., Tan, T., Huang, K., Jia, K. & Wu, X. (2009, A Study on Gait- Based Gender
Classification, IEEE Transactions on Image Processing 18(8):1905 1910.).
ResearchGate has not been able to resolve any citations for this publication.
Gender Classification In Two Emotional Speech Databases
Conference Paper
Full-text available
  • Dec 2008
Gender classification is a challenging problem, which finds applications in speaker indexing, speaker recognition, speaker diarization, annotation and retrieval of multimedia databases, voice synthesis, smart human-computer interaction, biometrics, social robots etc. Although it has been studied for more than thirty years, by no means it is a solved problem. Processing emotional speech in order to identify speaker’s gender makes the problem even more interesting. A large pool of 1379 features is created including 605 novel features. A branch and bound feature selection algorithm is applied to select a subset of 15 features among the 1379 originally extracted. Support vector machines with various kernels are tested as gender classifiers, when applied to two databases, namely: the Berlin database of Emotional Speech and the Danish Emotional Speech database. The reported classification results outperformthose obtained by state-of-the-art techniques, since a perfect classification accuracy is obtained.
View
A Study on Gait-Based Gender Classification
Article
Full-text available
  • Aug 2009
Gender is an important cue in social activities. In this correspondence, we present a study and analysis of gender classification based on human gait. Psychological experiments were carried out. These experiments showed that humans can recognize gender based on gait information, and that contributions of different body components vary. The prior knowledge extracted from the psychological experiments can be combined with an automatic method to further improve classification accuracy. The proposed method which combines human knowledge achieves higher performance than some other methods, and is even more accurate than human observers. We also present a numerical analysis of the contributions of different human components, which shows that head and hair, back, chest and thigh are more discriminative than other components. We also did challenging cross-race experiments that used Asian gait data to classify the gender of Europeans, and vice versa. Encouraging results were obtained. All the above prove that gait-based gender classification is feasible in controlled environments. In real applications, it still suffers from many difficulties, such as view variation, clothing and shoes changes, or carrying objects. We analyze the difficulties and suggest some possible solutions.
View
SUPPORT VECTOR MACHINE IN GENDER RECOGNITION
Article
  • Dec 2017
In the paper, Support Vector Machine (SVM) methods are discussed. The SVM algorithm is a very strong classification tool. Its capability in gender recognition in comparison with the other methods is presented here. Different sets of face features derived from the frontal facial image such as eye corners, nostrils, mouth corners etc. are taken into account. The efficiency of different sets of facial features in gender recognition using SVM method is examined.
View
Gender Classification from NIR Iris Images Using Deep Learning
Chapter
  • Aug 2017
Gender classification from NIR iris image is a new topic with only a few papers published. All previous work on gender-from-iris tried to find the best feature extraction techniques to represent the information of the iris texture for gender classification using normalized, encoded or periocular images. However this is a new topic in deep-learning application with soft biometric. In this chapter, we show that learning gender-iris representations through the use of deep neural networks may increase the performance obtained on these tasks. To this end, we propose the application of deep-learning methods to separate the gender-from-iris images even when the amount of learning data is limited, using an unsupervised stage with Restricted Boltzmann Machine (RBM) and a supervised stage using a Convolutional Neural Network (CNN).
View
View
Gender Classification From the Same Iris Code Used for Recognition
Article
Previous researchers have explored various approaches for predicting the gender of a person based on the features of the iris texture. This paper is the first to predict gender directly from the same binary iris code that could be used for recognition. We found that the information for gender prediction is distributed across the iris, rather than localized in particular concentric bands. We also found that using selected features representing a subset of the iris region achieves better accuracy than using features representing the whole iris region. We used the measures of mutual information to guide the selection of bits from the iris code to use as features in gender prediction. Using this approach, with a person-disjoint training and testing evaluation, we were able to achieve 89% correct gender prediction using the fusion of the best features of iris code from the left and right eyes.
View
Learning to predict gender from iris images
Conference Paper
  • Oct 2007
This paper employs machine learning techniques to develop models that predict gender based on the iris texture features. While there is a large body of research that explores biometrics as a means of verifying identity, there has been very little work done to determine if biometric measures can be used to determine specific human attributes. If it is possible to discover such attributes, they would be useful in situations where a biometric system fails to identify an individual that has not been enrolled, yet still needs to be identified. The iris was selected as the biometric to analyze for two major reasons: (1) quality methods have already been developed to segment and encode an iris image, (2) current iris encoding methods are conducive to selecting and extracting attributes from an iris texture and creating a meaningful feature vector.
View
Gender identification using frontal facial images
  • Jan 2005
  • A Jain
  • J Huang
  • S Fang
Jain, A., Huang, J., & Fang, S. (2005, Gender identification using frontal facial images, In Multimedia and Expo. ICME. IEEE International Conference on IEEE.