GÜRBÜZ YÜZ TANIMA İÇİN ÇOK-KİPLİ ÖZNİTELİK FÜZYONU

Abstract

Yüz tanıma çok sayıda uygulama alanı olan popüler bir bilgisayarla görü problemidir. Farklı ışık koşulları ve değişen yüz ifadeleri yüz tanıma problemini zorlaştıran etkenlerdir. Yüz tanıma işlemi için çeşitli yöntemlerle elde edilen öznitelikler yüze ait farklı karakteristik özellikleri yansıtır. Bu karakteristik özelliklerden faydalanılarak yüz tanıma işlemi gerçekleştirilir. Bu çalışmada, örüntü ve doku tanımada sıklıkla kullanılan Yerel İkili Örüntü ve Felzenszwalb Yönelimli Gradyan Histogram özniteliklerinin birleştirilmesi ile yüz tanıma problemine çok kipli bir çözüm sunulmuştur. Yüz imgesi bölgelere ayrılarak, her iki yöntem ile bölgelerden öznitelik vektörleri elde edilmiştir. Bununla birlikte elde edilen vektörlere öznitelik seçim yöntemleri uygulanarak hem vektör boyutu azaltılmış hem de başarım arttırılmıştır. Öznitelik seçimi sonucu her iki yöntem için seçilen öznitelik alt kümeleri birleştirilerek uzamsal ve spektral öznitelikleri içeren tek bir öznitelik vektörü haline getirilmiştir. Seçilen öznitelikler Ki-kare sınıflandırıcısı kullanılarak sınıflandırılmıştır. Önerilen yöntemin başarımı FERET veri setinde ölçülmüş, %89.45 yüz doğrulama ve %94.55 yüz tanıma başarımı elde edilmiştir.

Keywords

• Yüz Tanıma
• Öznitelik Çıkartma
• Öznitelik Birleştirme
• Spektral Öznitelikler
• Uzamsal Öznitelikler

FUSION OF SELECTED MULTI-MODAL FEATURES FOR ACCURATE FACE RECOGNITION

Abstract

Face recognition is a popular computer vision problem with many areas of application. Different lighting conditions and changing facial expressions are factors that make the face recognition problem difficult. The features extracted by different methods from the face image reflect the different characteristics of the face image. Face recognition process is applied by using these features. In this study, a multi-modal solution to the face recognition problem is presented by fusing the Local Binary Pattern and Felzenszwalb Histogram of Oriented Gradients features, which are frequently used in pattern and texture recognition. Face image is divided into regions and feature vectors are obtained from the regions through both methods. However, by applying feature selection methods to the obtained vectors, both the vector size is reduced and the performance is increased. As a result of the feature selection, the feature subsets selected for both methods are combined into a single feature vector containing spatial and spectral features. Selected features are classified using the Chi-square classifier. The success of the proposed method was measured in the FERET dataset, 89.45% verification success and 94.55% identification success were obtained.

Keywords

• Face Recognition
• Feature Extraction
• Feature Fusion
• Spectral Features
• Spatial Features

References

1. Dalal, Navneet, and Bill Triggs. "Histograms of oriented gradients for human detection." 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05). Vol. 1. Ieee, 2005.
2. Felzenszwalb, Pedro F., et al. "Object detection with discriminatively trained part-based models." IEEE transactions on pattern analysis and machine intelligence 32.9 (2009): 1627-1645.
3. Gacav, C., Topal, C., Benligiray B. (2017). Greedy search for descriptive spatial face features. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
4. Gacav, Caner, Burak Benligiray, and Cihan Topal. "Greedy search for descriptive spatial face features." 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2017.
5. Gacav, Caner, Burak Benligiray, and Cihan Topal. "Sequential forward feature selection for facial expression recognition." 2016 24th Signal Processing and Communication Application Conference (SIU). IEEE, 2016.
6. Gacav, Caner, et al. "Facial expression recognition with FHOG features." 2018 26th Signal Processing and Communications Applications Conference (SIU). IEEE, 2018.
7. Gusain, Raj, Hemant Jain, and Shivendra Pratap. "Enhancing bank security system using Face Recognition, Iris Scanner and Palm Vein Technology." 2018 3rd International Conference On Internet of Things: Smart Innovation and Usages (IoT-SIU). IEEE, 2018.
8. Holat, Recep, and Selman Kulaç. "YÜZ BULMA VE TANIMA SİSTEMLERİ KULLANARAK KİMLİK TANIMA ID IDENTIFICATION BY USING FACE DETECTION AND RECOGNITION SYSTEMS."

9. Huang, Y., Chen S. (2015). A Geometrical-Modal-Based Face Recognition. IEEE International Conference on Image Processing (ICIP).
10. Kazemi, Vahid, and Josephine Sullivan. "One millisecond face alignment with an ensemble of regression trees." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.
11. Kowsari, Kamran, et al. "Rmdl: Random multimodel deep learning for classification." Proceedings of the 2nd International Conference on Information System and Data Mining. 2018.
12. Last, Mark, Abraham Kandel, and Oded Maimon. "Information-theoretic algorithm for feature selection." Pattern Recognition Letters 22.6-7 (2001): 799-811.
13. Memiş, Abbas, and Fethullah Karabiber. "Face recognition on mobile environment images using appearance based methods." 2016 24th Signal Processing and Communication Application Conference (SIU). IEEE, 2016.
14. Nakariyakul, Songyot, and David P. Casasent. "An improvement on floating search algorithms for feature subset selection." Pattern Recognition 42.9 (2009): 1932-1940.
15. Ojala, Timo, Matti Pietikäinen, and David Harwood. "A comparative study of texture measures with classification based on featured distributions." Pattern recognition 29.1 (1996): 51-59.
16. Özbey, Nuri, and Cihan Topal. "Expression recognition with appearance-based features of facial landmarks." 2018 26th Signal Processing and Communications Applications Conference (SIU). IEEE, 2018.
17. Phillips, P. Jonathon, et al. "The FERET evaluation methodology for face-recognition algorithms." IEEE Transactions on pattern analysis and machine intelligence 22.10 (2000): 1090-1104.
18. Schenk, Joachim, Moritz Kaiser, and Gerhard Rigoll. "Selecting features in on-line handwritten whiteboard note recognition: SFS or SFFS?." 2009 10th international conference on document analysis and recognition. IEEE, 2009.
19. Taigman, Yaniv, et al. "Deepface: Closing the gap to human-level performance in face verification." Proceedings of the IEEE conference on computer vision and pattern recognition. 2014.
20. Viola, Paul, and Michael J. Jones. "Robust real-time face detection." International journal of computer vision 57.2 (2004): 137-154.
21. Yan, Mengjia, et al. "Vargfacenet: An efficient variable group convolutional neural network for lightweight face recognition." Proceedings of the IEEE/CVF International Conference on Computer Vision Workshops. 2019.
22. Yavuz, Hasan Serhan, Hakan Cevikalp, and Rifat Edizkan. "A comprehensive comparison of features and embedding methods for face recognition." Turkish Journal of Electrical Engineering & Computer Sciences 24.1 (2016): 313-340.