3D facial recognition using local feature-based methods and accuracy assessment

Öz

With laser scanning technology, making it easy to obtain a 3-dimensional point cloud has enabled the popularization of three-dimensional face recognition against the limitations of facial recognition performed using 2D images.In this study, the facial data of 10 people were modeled in 3D using a laser scanner. A total of 30 point clouds were taken from 10 people-two natural facial expressions and one laughing facial expression. The algorithm consists of three steps. In the first step, 3D points are defined on the point clouds using ISS and LSP methods. In the second step, key points were described using PFH and FPFH methods to obtain feature histogram. In the third step, the keypoints in different point clouds were matched using the feature histograms via Kullbeck-Leiber Divergence method. For accuracy analysis, point clouds are registered with Iterative Closest Point (ICP) method. For accuracy assessment, the Euclidean distance between the matching points was calculated. The ISS algorithm finds about 25% less points than the LSP algorithm. The correct matching rate for PFH is up to 60%, while FPFH histograms are around 25%-30%.

Anahtar Kelimeler

• Local feature,face recognition,point cloud,laser scanning,accuracy assessment

Lokal özellik temelli yöntemler kullanılarak 3B yüz tanıma ve doğruluk analizi

Öz

Lazer tarama teknolojisinin gelişmesiyle 3 boyutlu nokta bulutu elde etmenin kolay hale gelmesi, 2B görüntüler kullanılarak gerçekleştirilen yüz tanıma işleminin kısıtlamalarına karşı üç boyutlu yüz tanımanın popülerleşmesini sağlamıştır. Bu çalışmada 10 kişiye ait yüz verisi lazer tarayıcı kullanılarak 3 boyutlu olarak modellenmiştir. İki farklı doğal yüz ifadesi ve bir gülme yüz ifadesi olmak üzere 10 kişiden toplamda 30 adet nokta bulutu alınmıştır. Algoritma 3 adımdan oluşmaktadır. İlk adımda ISS VE LSP yöntemleri kullanılarak nokta bulutları üzerinde 3B ilgi noktaları belirlenmiştir. İkinci adımda, PFH ve FPFH yöntemleri kullanılarak ilgi noktaları tanımlanmıştır. Böylece her birine ait özellik histogramı elde edilmiştir. Üçüncü adımda, özellik histogramları kullanılarak farklı nokta bulutlarındaki ilgi noktaları eşleştirilmiştir. Bu amaçla Kullbeck-Leibler Divergence yöntemi kullanılmıştır. İlgi noktası bulucu ve tanımlayıcı algoritmaların kombinasyonları çalışma sonucunda karşılaştırılmıştır. Doğruluk analizi için nokta bulutları İteratif En Yakın Nokta (İEYN)(ICP) yöntemiyle çakıştırılmıştır. Eşlenik noktaların arasındaki Öklid mesafesi hesaplanarak doğru eşlenen noktalar tespit edilmiştir. ISS algoritması LSP algoritmasına göre yaklaşık %25 oranında daha az nokta bulmaktadır. PFH kullanılarak yapılan eşlemelerde doğru eşleme oranı %60’lara ulaşırken, FPFH histogram ile yapılan eşleştirmeler ise %25-%30 dolaylarında kalmıştır.

Anahtar Kelimeler

• Lokal özellik,yüz tanıma,nokta bulutu,lazer tarama,doğruluk analizi

Kaynakça

1. 1. Kakadiaris, I. A., Toderici, G., Evangelopoulos, G., Passalis, G., Chu, D., Zhao, X., Theoharis, T., 3D-2D face recognition with pose and illumination normalization, Computer Vision and Image Understanding, 154, 137-151, 2017.
2. 2. Soltanpour, S., Boufama, B., Wu, Q. J., A survey of local feature methods for 3D face recognition, Pattern Recognition, 72, 391-406, 2017.
3. 3. Berretti, S., Werghi, N., Del Bimbo, A., Pala, P., Matching 3D face scans using interest points and local histogram descriptors, Computers & Graphics, 37(5), 509-525, 2013.
4. 4. Hariri, W., Tabia, H., Farah, N., Benouareth, A., Declercq, D., 3D face recognition using covariance based descriptors, Pattern Recognition Letters, 78, 1-7, 2016.
5. 5. Akyol, O., Duran, Z., Low-cost laser scanning system design, Journal of Russian Laser Research, 35(3), 244-251, 2014.
6. 6. Salti, S., Tombari, F., Spezialetti, R., Di Stefano, L., Learning a descriptor-specific 3D keypoint detector, In Proceedings of the IEEE International Conference on Computer Vision, 2318-2326, 2015.
7. 7. Hänsch, R., Weber, T., Hellwich, O., Comparison of 3D interest point detectors and descriptors for point cloud fusion, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2(3), 57, 2014.
8. 8. Scheenstra, A., Ruifrok, A., Veltkamp, R. C., A survey of 3d face recognition methods, In International Conference on Audio-and Video-based Biometric Person Authentication, 891-899, Springer, Berlin, Heidelberg, 2005.

9. 9. Bowyer, K. W., Chang, K., Flynn, P., A survey of approaches and challenges in 3D and multi-modal 3D+ 2D face recognition, Computer vision and image understanding, 101(1), 1-15, 2006.
10. 10. Romero, M., Pears, N., Landmark localisation in 3d face data, In 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, 73-78, 2009.
11. 11. Mian, A. S., Bennamoun, M., Owens, R., Keypoint detection and local feature matching for textured 3D face recognition, International Journal of Computer Vision, 79(1), 1-12, 2008.
12. 12. Phillips, P. J., Flynn, P. J., Scruggs, T., Bowyer, K. W., Chang, J., Hoffman, K., Worek, W., Overview of the face recognition grand challenge, In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR'05), Vol. 1, 947-954, 2005.
13. 13. Mayo, M., Zhang, E., 3D face recognition using multiview keypoint matching, In 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance, 290-295, 2009.
14. 14. Moreno, A., GavabDB: a 3D face database, In Proc. 2nd COST275 Workshop on Biometrics on the Internet, 75-80, 2004.
15. 15. Lowe, D. G., Distinctive image features from scale-invariant keypoints, International Journal of Computer Vision, 60(2), 91-110, 2004.
16. 16. Huang, D., Zhang, G., Ardabilian, M., Wang, Y., Chen, L., 3D face recognition using distinctiveness enhanced facial representations and local feature hybrid matching., In 2010 Fourth IEEE International Conference on Biometrics: Theory, Applications and Systems (BTAS), 1-7, 2010.
17. 17. Inan, T., Halici, U., 3-D face recognition with local shape descriptors, IEEE transactions on Information Forensics and Security, 7(2), 577-587, 2012.
18. 18. Li, H., Huang, D., Lemaire, P., Morvan, J. M., & Chen, L., Expression robust 3D face recognition via mesh-based histograms of multiple order surface differential quantities, In 2011 18th IEEE International Conference on Image Processing, 3053-3056, 2011.
19. 19. Smeets, D., Keustermans, J., Vandermeulen, D., Suetens, P., meshSIFT: Local surface features for 3D face recognition under expression variations and partial data, Computer Vision and Image Understanding, 117(2), 158-169, 2013.
20. 20. Savran, A., Alyüz, N., Dibeklioğlu, H., Çeliktutan, O., Gökberk, B., Sankur, B., Akarun, L., Bosphorus database for 3D face analysis, In European Workshop on Biometrics and Identity Management, 47-56, Springer, Berlin, Heidelberg, 2008.
21. 21. Veltkamp, R. C., van Jole, S., Drira, H., Amor, B. B., Daoudi, M., Li, H., Vandermeulen, D., SHREC'11 Track: 3D Face Models Retrieval. In 3DOR, 89-95, 2011.
22. 22. Berretti, S., Werghi, N., Del Bimbo, A., Pala, P., Selecting stable keypoints and local descriptors for person identification using 3D face scans, The Visual Computer, 30(11), 1275-1292, 2015.
23. 23. Li, H., Huang, D., Morvan, J. M., Wang, Y., Chen, L. Towards 3D face recognition in the real: a registration-free approach using fine-grained matching of 3D keypoint descriptors, International Journal of Computer Vision, 113(2), 128-142, 2015.
24. 24. Elaiwat, S., Bennamoun, M., Boussaïd, F., El-Sallam, A., A curvelet-based approach for textured 3D face recognition. Pattern Recognition, 48(4), 1235-1246, 2015.
25. 25. Yin, L., Wei, X., Sun, Y., Wang, J., Rosato, M. J., A 3D facial expression database for facial behavior research, In 7th international conference on automatic face and gesture recognition (FGR06), 211-216, 2006.
26. 26. Guo, Y., Lei, Y., Liu, L., Wang, Y., Bennamoun, M., Sohel, F., EI3D: Expression-invariant 3D face recognition based on feature and shape matching, Pattern Recognition Letters, 83, 403-412, 2016.
27. 27. Abbad, A., Abbad, K., Tairi, H., 3D face recognition: Multi-scale strategy based on geometric and local descriptors, Computers & Electrical Engineering, 70, 525-537, 2018.
28. 28. Zhong, Y., Intrinsic shape signatures: A shape descriptor for 3d object recognition, In 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops, 689-696, 2009.
29. 29. Chen, H., Bhanu, B., 3D free-form object recognition in range images using local surface patches, Pattern Recognition Letters, 28(10), 1252-1262, 2007.
30. 30. Rusu, R. B., Marton, Z. C., Blodow, N., Beetz, M., Persistent point feature histograms for 3D point clouds, In Proc 10th Int Conf Intel Autonomous Syst (IAS-10), Baden-Baden, Germany, 119-128, 2008.
31. 31. Rusu, R. B., Blodow, N., Beetz, M., Fast point feature histograms (FPFH) for 3D registration, In 2009 IEEE international conference on robotics and automation, 3212-3217, 2009.
32. 32. Avşar, E. Ö., Bozkurtoğlu, E., Aydar, U., Şeker, D. Z., Kaya, Ş., Gazioğlu, C., Determining roughness angle of limestone using optical laser scanner, International Journal of Environment and Geoinformatics, 3(3), 57-75, 2016.
33. 33. Duran, Z., Aydar, U., Digital modeling of world's first known length reference unit: The Nippur cubit rod, Journal of cultural heritage, 13(3), 352-356, 2012.
34. 34. Yıldız, F., Altuntaş, C., Georeferencing Methods for Terrestrial Laser Scanner Poınt Clouds, Harita Dergisi, 142, 51-58, 2009.
35. 35. Boehler, W., Marbs, A., 3D scanning instruments. Proceedings of the CIPA WG, 6(9), 2002.
36. 36. Dorai, C., Jain, A. K., COSMOS-A representation scheme for 3D free-form objects, IEEE Transactions on Pattern Analysis and Machine Intelligence, 19(10), 1115-1130, 1997.
37. 37. Tombari, F., Salti, S., Di Stefano, L., Performance evaluation of 3D keypoint detectors, International Journal of Computer Vision, 102(1-3), 198-220, 2013.
38. 38. Guo, Y., Bennamoun, M., Sohel, F., Lu, M., Wan, J., Kwok, N. M., A comprehensive performance evaluation of 3D local feature descriptors, International Journal of Computer Vision, 116(1), 66-89, 2016.
39. 39. He, Y., Liang, B., Yang, J., Li, S., He, J. An iterative closest points algorithm for registration of 3D laser scanner point clouds with geometric features, Sensors, 17(8), 1862, 2017.