Yüz İfadesi Tanıma için Mesafe Oranlarına Dayalı Öznitelik Çıkarımı ve Genetik Algoritmalar ile Seçimi

Yıl 2019, Cilt: 2 Sayı: 1, 19 - 29, 13.07.2019

Ensar Arif Sağbaş Osman Gökalp Aybars Uğur

Öz

Yüz ifadeleri, insanların
duyguları hakkında bilgi vermesi nedeniyle sözsüz iletişimde önemli bir rol
oynamaktadır ve başta eğitim, sağlık, hukuk, eğlence olmak üzere çok çeşitli
alanlarda kullanılmaktadır. Bu çalışmada yüz ifadelerine dayalı duygu tespiti sistemi
geliştirilmiştir. Bu kapsamda yedi temel duygu ifadesi için (mutlu, kızgın,
üzgün, iğrenme, korku, şaşırma ve nötr) toplam 9296 adet görüntü 4 erkek 3
kadın katılımcıdan alınmıştır. Elde edilen görüntüler kullanılarak öncelikle
yüz işaretçilerinin konumu tespit edilmiştir. Sonrasında yüz işaretçileri
arasındaki mesafe oranlarına dayalı yeni bir öznitelik çıkarma yaklaşımı ile
toplamda 120 adet öznitelik çıkartılmıştır. Öznitelik seçiminde Genetik
Algoritmalar kullanılmıştır. Buna ek olarak ReliefF, Information Gain ve Gain
Ratio öznitelik seçimi algoritmalarının başarımı Genetik Algoritmaların sonucu
ile karşılaştırılmıştır. Seçilen özniteliklerin sınıflandırma performansları;
kNN, Bayes Ağları ve Rastgele Orman yöntemleri ile test edilmiştir. Sonuç olarak,
bu çalışmada önerilen öznitelik çıkarma yöntemi ile elde edilen özniteliklerin
Genetik Algoritmalar kullanılarak seçilmesi ve Rastgele Orman ile
sınıflandırılmasının ardından başarılı sonuçlar üretebildiği gözlemlenmiştir.

Anahtar Kelimeler

Yüz ifadesi tanıma, makine öğrenmesi, öznitelik seçimi, genetik algoritmalar, öznitelik çıkarımı

Kaynakça

• [1] Hariri W, Tabia H, Farah N, Benouareth A, Declercq D. “3D facial expression recognition using kernel methods on Riemannian manifold”. Engineering Applications of Artificial Intelligence, 64, 25-32, 2017.
• [2] Zeng N, Zhang H, Song B, Liu W, Li Y, Dobaie AM. “Facial expression recognition via learning deep sparse autoencoders”. Neurocomputing, 273, 643-649, 2018.
• [3] Ekman P, Friesen WV. “Constants across cultures in the face and emotion”. Journal of personality and social psychology, 17(2), 124, 1971.
• [4] Chandrashekar G, Sahin F. “A survey on feature selection methods”. Computers & Electrical Engineering, 40(1), 16-28, 2014.
• [5] Soyel H, Demirel H. “Optimal feature selection for 3D facial expression recognition using coarse-to-fine classification”. Turkish Journal of Electrical Engineering & Computer Sciences, 18(6), 1031-1040, 2010.
• [6] Yang H, Yin L. “CNN based 3D facial expression recognition usin masking and landmark features”. In Affective Computing and Intelligent Interaction, San Antonio, Texas, 23-26 October 2017.
• [7] Owusu E, Zhan Y, Mao QR. “A neural-AdaBoost based facial expression recognition system”. Expert Systems with Applications, 41(7), 3383-3390, 2014.
• [8] Ruiz LZ, Alomia RPV, Dantis ADQ, San Diego MJS, Tindugan CF, Serrano KKD. “Human emotion detection through facial expressions for commercial analysis”. In Humanoid, Nanotechnology, Information Technology, Manila, Philippines, 1-3 December 2017.
• [9] Ayvaz U, Gürüler H. “Real-time detection of students’ emotiona states in the classroom”. In Signal Processing and Communications Applications Conference, Antalya, Türkiye, 15-18 Mayıs 2017.
• [10] Agrawal, S., & Khatri, P. (2015, February). “Facial expression detection techniques: based on Viola and Jones algorithm and principal component analysis”. In Advanced Computing & Communication Technologies, Rohtak, India, 21-22 February 2015.
• [11] Tivatansakul S, Ohkura M, Puangpontip S, Achalakul T. (2014, September). “Emotional healthcare system: Emotion detection by facial expressions using Japanese database”. In Computer Science and Electronic Engineering Conference, Colchester, United Kingdom, 25-26 September 2014.
• [12] Lajevardi SM, Hussain ZM. “Feature selection for facial expression recognition based on optimization algorithm”. In Nonlinear Dynamics and Synchronization, Klagenfurt, Austria, 20-21 July 2009.
• [13] Ayvaz, U., Gürüler, H., & Devrim, M. O. (2017). Use of Facial Emotion Recognition in e-learning Systems. Information Technologies and Learning Tools, 60(4), 95-104.
• [14] Gacav, C., Benligiray, B., Özkan, K., & Topal, C. (2018, May). Facial expression recognition with FHOG features. In 2018 26th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• [15] Engin, D., & Ekenel, H. K. (2017, May). Facial expression pair matching. In Signal Processing and Communications Applications Conference (SIU), 2017 25th (pp. 1-4). IEEE.
• [16] Gacav, C., Benligiray, B., & Topal, C. (2016, May). Sequential forward feature selection for facial expression recognition. In Signal Processing and Communication Application Conference (SIU), 2016 24th (pp. 1481-1484). IEEE.
• [17] Özbey, N., & Topal, C. (2018, May). Expression recognition with appearance-based features of facial landmarks. In 2018 26th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• [18] Aksoy, N., & Sert, M. (2016, May). Facial action unit detection using variable decision thresholds. In Signal Processing and Communication Application Conference (SIU), 2016 24th (pp. 2185-2188). IEEE.
• [19] Akkoca, B. S., & Gökmen, M. (2015, May). Automatic smile recognition from face images. In Signal Processing and Communications Applications Conference (SIU), 2015 23th (pp. 1985-1988). IEEE.
• [20] Akyol, F., & Şahin, P. D. (2016, May). Image-based facial expression detection. In Signal Processing and Communication Application Conference (SIU), 2016 24th (pp. 609-612). IEEE.
• [21] Bayrakdar, S., Akgün, D., & Yücedağ, İ. (2017). Video dosyaları üzerinde yüz ifade analizi için hızlandırılmış bir yaklaşım. Pamukkale University Journal of Engineering Sciences, 23(5). pp. 602-613.
• [22] Ayvaz, U., & Gürüler, H. (2017). Bilgisayar Kullanıcılarına Yönelik Duygusal İfade Tespiti. Bilişim Teknolojileri Dergisi, 10(2), 231-239.
• [23] Li J, Zhang D, Zhang J, Zhang J, Li T, Xia Y, Xun L. “Facial Expression Recognition with Faster R-CNN”. Procedia Computer Science, 107, 135-140, 2017.
• [24] Tümen, V., Söylemez, Ö. F., & Ergen, B. (2017, September). Facial emotion recognition on a dataset using convolutional neural network. In Artificial Intelligence and Data Processing Symposium (IDAP), 2017 International (pp. 1-5). IEEE.
• [25] Abanoz, H., & Çataltepe, Z. (2018, May). Emotion recognition on static images using deep transfer learning and ensembling. In 2018 26th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• [26] Akay, S., & Arica, N. (2018, May). Facial action unit detection using deep neural networks in videos. In 2018 26th Signal Processing and Communications Applications Conference (SIU) (pp. 1-4). IEEE.
• [27] Kononenko, I. (1994). “Estimating attributes: analysis and extensions of RELIEF”. In European conference on machine learning, Catania, Italy, 6-8 April 1994.
• [28] Peker M, Arslan A, Sen B, Celebi FV, But A. (2015, September). “A novel hybrid method for determining the depth of anesthesia level: Combining ReliefF feature selection and random forest algorithm (ReliefF+RF)”. In Innovations in Intelligent SysTems and Applications Madrid, Spain, 2-4 September 2015.
• [29] S. Lei, “A feature selection method based on information gain and genetic algorithm”, International Conference on Computer Science and Electronics Engineering, Hangzhou, China 23-25 March 2012.
• [30] Uğuz H. “A two-stage feature selection method for text categorization by using information gain, principal component analysis and genetic algorithm”. Knowledge-Based Systems, 24(7), 1024-1032, 2011.
• [31] Karegowda AG, Manjunath AS, Jayaram MA. “Comparative study of attribute selection using gain ratio and correlation based feature selection”. International Journal of Information Technology and Knowledge Management, 2(2), 271-277, 2010.
• [32] Yazıcı B, Yaslı F, Gürleyik HY, Yurgut UO., Aktas MS, Kalıpsız O. “Veri Madenciliğinde Özellik Seçim Tekniklerinin Bankacılık Verisine Uygulanması Üzerine Araştırma ve Karşılaştırmalı Uygulama”. In Proceedings of the 9th Turkish National Software Engineering Symposium, Izmir, Turkey, 9-11 September 2015.
• [33] Holland, J. H., 1975, Adaptation In Natural And Artificial Systems: an introductory analysis with applications to biology, control, and artificial intelligence, University of Michigan Press, 1975.
• [34] Ben‐Gal I. Bayesian Networks. Editors: Fabrizio Ruggeri, Ron Kenett and Frederick Faltin. Encyclopedia of Statistics in Quality and Reliability. Chichester, UK, Wiley; 2007.
• [35] Feng T, Timmermans HJ. “Transportation mode recognition using GPS and accelerometer data”. Transportation Research Part C: Emerging Technologies, 37, 118-130, 2013.
• [36] Alsberg BK, Goodacre R, Rowland, JJ, Kell DB. “Classification of pyrolysis mass spectra by fuzzy multivariate rule induction-comparison with regression, K-nearest neighbour, neural and decision-tree methods”. Analytica Chimica Acta, 348(1), 389-407, 1997.
• [37] Özkan Y, Erol Ç. Biyoenformatik DNA Mikrodizi Veri Madenciliği, İstanbul, Türkiye, Papatya Yayıncılık Eğitim, 2015.
• [38] Morizet N, Godin N, Tang J, et al. Classification of acoustic emission signals using wavelets and random forests: application to localized corrosion. Mech Syst Signal Pr 2016; 70: 1026–1037.
• [39] Adrian Rosebrock. “Facial landmarks with dlib, OpenCV, and Python”. https://www.pyimagesearch.com/2017/04/03/facial-landmarks-dlib-opencv-python/ (12.07.2018)
• [40] Frank E, Hall MA, Witten IH. The WEKA Workbench. Online Appendix for "Data Mining: Practical Machine Learning Tools and Techniques, Dördüncü baskı, Cambridge, MA, United States, Morgan Kaufmann, 2016.