İmge Kümeleriyle Yüz Tanıma için Otomatik Önişleme

Otomatik yüz tanıma süreci son yıllarda popülerliğini arttırmış bir konudur. İmge tabanlı yaklaşımların hâkim olduğu yüz tanıma süreci, kamera ve hesaplama teknolojilerinin gelişimiyle yerini video tabanlı yaklaşımlara bırakmaktadır. Video tabanlı yüz tanıma uygulamalarında, özellikle kişilerin farklı aydınlatma veya cepheden, yandan görünüm vb. farklı pozlar içeren imge kümelerinin eşleştirilmesi zorluklar içermektedir. Bu çalışmada, özellikle aydınlatma ve poz çeşitliliklerinin var olduğu durumlarda, küme tabanlı yüz tanıma yöntemlerinin başarımlarının nasıl iyileştirilebileceği araştırılmıştır. Ön işleme basamağında, aydınlatma farklılıkları giderildikten sonra imgeler öncelikle yüz pozuna göre sınıflandırılmıştır. Pozlara göre ayrıştırılan yüzler, sınıf içi değişimlerinin azaltılması için ilgili pozun şablonuna hizalanmıştır. Yapılan deneyler sonucunda, önişleme basamağında önerilen otomatik poz hizalama yöntemi kullanıldığında, video tabanlı yüz tanıma deneylerinin başarım oranlarında gelişmeler sağlandığı tespit edilmiştir.

Anahtar Kelimeler:

yüz sezimi, yüz hizalama, yüz tanıma, imge kümeleri

Autonomous Preprocessing for Image Set Based Face Recognition

Automatic face recognition process has become a popular topic in recent years. The facial recognition process, where previously single-image based methods were more common, has started to leave its place in video-based approaches by the development of camera and computing technologies. In video based recognition applications, it becomes more difficult to match the image sets of the same person whose frames captured under different illumination conditions or when the compared frames include different face poses such as frontal versus profile. In this study, we investigate how to improve the accuracies of set based face recognition methods in case of lighting and face pose variations. At the pre-processing stage, after the illumination differences are refined, the images are firstly classified according to face exposure. The faces that are separated according to the poses are aligned to the corresponding canonical pose patterns to reduce intra class variations. Experimental results demonstrate that set based recognition methods give higher correct recognition rates when the proposed methodology schemes have been applied as a preprocessing stage.

Keywords:

face detection, face alignment, face recognition, image sets,

PDF

___

Ahonen, T., Hadid, A., & Pietikainen, M. (2006). Face description with local binary patterns: Application to face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 28 (12), 2037-2041. doi: 10.1109/tpami.2006.244
Cevikalp, H., & Triggs, B. (2010). Face recognition based on image sets. In 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE. doi: 10.1109/cvpr.2010.5539965
Chelali, F., Djeradi, A., & Djeradi, R. (2009). Linear discriminant analysis for face recognition. In 2009 international conference on multimedia computing and systems. IEEE. doi: 10.1109/mmcs.2009.5256630
Gross, R., & Shi, J. (2001). The cmu motion of body (mobo) database (Tech. Rep. No. CMU-RI-TR-01-18). Pittsburgh, PA: Carnegie Mellon University.
Harandi, M. T., Sanderson, C., Shirazi, S., & Lovell, B. C. (2013). Kernel analysis on Grassmann manifolds for action recognition. Pattern Recognition Letters, 34 (15), 1906-1915. doi: 10.1016/j.patrec.2013.01.008
Hassaballah, M., & Aly, S. (2015). Face recognition: challenges, achievements and future directions. IET Computer Vision, 9 (4), 614-626. doi: 10.1049/iet-cvi.2014.0084
Hu, Y., Mian, A. S., & Owens, R. (2012). Face recognition using sparse approximated nearest points between image sets. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34 (10), 1992-2004. doi: 10.1109/TPAMI.2011.283
Intraface. (2018, oct). Intraface software, the human sensing laboratory of carnegie mellon university. Retrieved from http://www.humansensing.cs.cmu.edu/software
Kim, M., Kumar, S., Pavlovic, V., & Rowley, H. (2008). Face tracking and recognition with visual constraints in real-world videos. In 2008 IEEE conference on computer vision and pattern recognition. IEEE. doi: 10.1109/cvpr.2008.4587572
Lee, K.-C., Ho, J., Yang, M.-H., & Kriegman, D. (2005). Visual tracking and recognition using probabilistic appearance manifolds. Computer Vision and Image Understanding, 99 (3), 303-331. doi: 10.1016/j.cviu.2005.02.002
Li, S. Z., & Jain, A. K. (Eds.). (2011). Handbook of face recognition. Springer London.
Li, Z., Lin, D., & Tang, X. (2009). Nonparametric discriminant analysis for face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31 (4), 755-761. doi: 10.1109/tpami.2008.174
Lienhart, R., & Maydt, J. (2002). An extended set of haar-like features for rapid object detection. In proceedings of international conference on image processing. IEEE. doi: 10.1109/icip.2002.1038171
Liu, C. (2004). Gabor-based kernel pca with fractional power polynomial models for face recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26 (5), 572-581. doi: 10.1109/tpami.2004.1273927
Lu, J., Plataniotis, K., & Venetsanopoulos, A. (2003). Face recognition using kernel direct discriminant analysis algorithms. IEEE Transactions on Neural Networks, 14 (1), 117-126. doi: 10.1109/tnn.2002.806629
Lu, J., Wang, G., & Zhou, J. (2017). Simultaneous feature and dictionary learning for image set based face recognition. IEEE Transactions on Image Processing, 26 (8), 4042-4054. doi: 10.1109/tip.2017.2713940
Mika, S., Ratsch, G., Weston, J., Scholkopf, B., & Mullers, K. (1999). Fisher discriminant analysis with kernels. In Neural networks for signal processing IX: Proceedings of the 1999 IEEE signal processing society workshop (cat. no.98th8468). IEEE. doi: 10.1109/nnsp.1999.788121
Nhat, V. D. M., & Lee, S. (2007). Kernel-based 2dpca for face recognition. In 2007 IEEE international symposium on signal processing and information technology. IEEE. doi: 10.1109/isspit.2007.4458104
OpenCV. (2018, dec). Open source computer vision (opencv) library. Retrieved from https://opencv.org/
Scholkopf, B., Smola, A., & Muller, K.-R. (1997). Kernel principal component analysis. In Lecture notes in computer science (pp. 583{588). Springer Berlin Heidelberg. doi: 10.1007/bfb0020217
Shi, B., Bai, X., Liu, W., & Wang, J. (2018). Face alignment with deep regression. IEEE Transactions on Neural Networks and Learning Systems, 29 (1), 183-194. doi: 10.1109/tnnls.2016.2618340
Tistarelli, M., & Champod, C. (Eds.). (2017). Handbook of biometrics for forensic science. Springer International Publishing. doi: 10.1007/978-3-319-50673-9
Turk, M., & Pentland, A. (1991). Eigenfaces for recognition. Journal of Cognitive Neuroscience, 3 (1), 71-86. doi: 10.1162/jocn.1991.3.1.71
Vinay, A., Shekhar, V., Murthy, K. B., & Natarajan, S. (2015). Face recognition using gabor wavelet features with PCA and KPCA - a comparative study. Procedia Computer Science, 57 , 650-659. doi: 10.1016/j.procs.2015.07.434
Viola, P., & Jones, M. (2001). Robust real-time object detection. International Journal of Computer Vision, 57, 137-154. doi: 10.1023/B:VISI.0000013087.49260.fb
Wang, H., Wang, Y., & Cao, Y. (2009). Video-based face recognition: A survey. World Academy of Science, Engineering and Technology, 2 , 136-139. doi: 10.1007/978-1-84882-385-3_8
Wang, R., Shan, S., Chen, X., Dai, Q., & Gao, W. (2012). Manifold-manifold distance and its application to face recognition with image sets. IEEE Transactions on Image Processing, 21 (10), 4466-4479. doi: 10.1109/tip.2012.2206039
Wiskott, L., Fellous, J.-M., Kruger, N., & von der Malsburg, C. (1997). Face recognition by elastic bunch graph matching. In Computer analysis of images and patterns (pp. 456-463). Springer Berlin Heidelberg. doi: 10.1007/3-540-63460-6_150
Wu, Y., & Ji, Q. (2018). Facial landmark detection: A literature survey. International Journal of Computer Vision. doi: 10.1007/s11263-018-1097-z
Xiong, X., & De La Torre, F. (2013). Supervised descent method and its applications to face alignment. In Proceedings of the ieee computer society conference on computer vision and pattern recognition (pp. 532-539). doi: 10.1109/CVPR.2013.75
Yalcin, M., Cevikalp, H., & Yavuz, H. S. (2015). Towards large-scale face recognition based on videos. In 2015 IEEE international conference on computer vision workshop (ICCVW). IEEE. doi: 10.1109/iccvw.2015.141
Yamaguchi, O., Fukui, E., & Maeda, K. (1998). Face recognition using temporal image sequence. In proceedings third IEEE international conference on automatic face and gesture recognition. IEEE. doi: 10.1109/afgr.1998.670968
Yang, M., Wang, X., Liu, W., & Shen, L. (2017). Joint regularized nearest points for image set based face recognition. Image and Vision Computing, 58 , 47-60. doi: 10.1016/j.imavis.2016.07.008
Yang, M., Zhu, P., Gool, L. V., & Zhang, L. (2013). Face recognition based on regularized nearest points between image sets. In 2013 10th IEEE international conference and workshops on automatic face and gesture recognition (FG). IEEE. doi: 10.1109/fg.2013.6553727
Yang, M. H., Kriegman, D. J., & Ahuja, N. (2002). Detecting faces in images: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 24 (1), 34-58. doi: 10.1109/34.982883
Yavuz, H. S., Cevikalp, H., & Edizkan, R. (2013). Automatic face recognition from frontal images. In 2013 21st signal processing and communications applications conference (SIU). IEEE. doi: 10.1109/SIU.2013.6531215
Zhao, J., Han, J., & Shao, L. (2018). Unconstrained face recognition using a set-to-set distance measure on deep learned features. IEEE Transactions on Circuits and Systems for Video Technology, 28 (10), 2679-2689. doi: 10.1109/tcsvt.2017.2710120
Zhou, E., Fan, H., Cao, Z., Jiang, Y., & Yin, Q. (2013). Extensive facial landmark localization with coarse-to-fine convolutional network cascade. In Proceedings of the ieee international conference on computer vision (pp. 386-391). doi: 10.1109/ICCVW.2013.58
Zhu, X., & Ramanan, D. (2012). Face detection, pose estimation, and landmark localization in the wild. In Proceedings of the ieee computer society conference on computer vision and pattern recognition (pp. 2879-2886). doi: 10.1109/CVPR.2012.6248014