Аннотация.

В статье предлагается метод пространственно-взвешенной нормализации яркости изображений лиц в градациях серого, который сохраняет значимую информацию при яркостной нормализации. Проводится экспериментальное исследование влияния различных вариантов яркостной нормализации на точность работы фиксированного нейросетевого классификатора в задаче верификации. Экспериментально показывается, что яркостная нормализация может повысить точность верификации для изображений лиц при сложном освещении и компенсировать не представленные в обучающих данных примеры.

Ключевые слова:

верификация изображений лиц, биометрия, яркостная нормализация, обработка изображений.

Стр. 12-20.

DOI 10.14357/20718632190402

Полная версия статьи в формате pdf. 

Литература

1. Zou X., Kittler J., Messer K. Illumination invariant face recognition: A survey // First IEEE International Conference on Biometrics: Theory, Applications, and Systems, 2007. – IEEE, 2007. - P.1–8.
2. Wang M., Deng W. Deep face recognition: A survey // arXiv preprint 1804.06655. - 2018.
3. Taigman Y. et al. Deepface: Closing the gap to humanlevel performance in face verification // In Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition. – IEEE, 2014. - P. 1701–1708.
4. Sun Y. at al. Deep learning face representation by joint identification-verification // In Proceedings of the 27th International Conference on Neural Information Processing Systems (NIPS’14.). - MIT Press, Cambridge, MA, USA. 2014. – V. 2. - P. 1988–1996.
5. Huang G. B., Learned-Miller E. Labeled faces in the wild: Updates and new reporting procedures // Tech. Rep.UM-CS- 2014-003. - University of Massachusetts, Amherst, 2014.
6. Amos B., Ludwiczuk B., Satyanarayanan M. Openface: A general-purpose face recognition library with mobile applications // Tech. rep., CMU-CS-16-118. - CMU School of Computer Science, 2016.
7. Schroff F., Kalenichenko D., Philbin J. Facenet: A unified embedding for face recognition and clustering // In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. – IEEE, 2015. - P. 815-823.
8. Crispell D. E. et al. Dataset augmentation for pose and lighting invariant face recognition // arXiv preprint arXiv:1704.04326. 2017.
9. Banerjee S. et al. Srefi: Synthesis of realistic example face images // In IEEE International Joint Conference on Biometrics (IJCB). – IEEE, 2017. P. 37–45.
10. Bao J. et al. Towards open-set identity preserving face synthesis // arXiv preprint arXiv: 1803.11182. - 2018.
11. Huang H. et al. Variational capsules for image analysis and synthesis // arXiv preprint arXiv: 1807.04099. - 2018.
12. Ghazi M. M., Ekenel H. K. A comprehensive analysis of deep learning based representation for face recognition // In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops (2016). – IEEE, 2016. – P. 34–41.
13. Peng B., Yang H., Li D., Zhang Z. An empirical study of face recognition under variations // In Proceedings of the 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018). - IEEE, 2018. – P. 310–317.
14. Ren J., Jiang X., Yuan J. A complete and fully automated face verification system on mobile devices // Pattern Recognition – 2013. – V. 46. – №. 1. - P. 45–56.
15. Chen S., Liu Y., Gao X., Han Z. Mobilefacenets: efficient CNNs for accurate real-time face verification on mobile devices // arXiv preprint arXiv: 1804.07573. - 2018.
16. Usilin S. et al. Visual appearance based document image classification // In Proceedings of the 17th IEEE International Conference on Image Processing (ICIP 2010). – IEEE, 2010. – P. 2133–2136.
17. Bulatov K. et al. Smart IDReader: Document recognition in video stream // In Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition (ICDAR 2017). – IEEE, 2017. – V. 06. - P. 39–44.
18. Skoryukina N. et al. Document localization algorithms based on feature points and straight lines // Tenth International Conference on Machine Vision (ICMV 2017). – International Society for Optics and Photonics, 2018. – V. 10696 - P. 106961H.
19. Winarski T. Y. Selfie financial security transaction system // US Patent App. 14/634,774. – 2016.
20. Cook S. Selfie banking: is it a reality? // Biometric Technology Today. – 2017. - №3. – P. 9–11.
21. Folego G. et al. Cross-domain face verification: Matching ID document and self-portrait photographs // arXiv preprint arXiv:1611.05755. – 2016.
22. Oliveira J. S. et al. Cross-domain deep face matching for real banking security systems // arXiv preprint arXiv:1806.07644. – 2018.
23. Starovoitov V., Samal D., Briliuk D. Three approaches for face recognition // The 6-th International Conference on Pattern Recognition and Image Analysis. - Velikiy Novgorod, Russia, 2002. – P. 21–26.
24. Bourlai T., Ross A., Jain A. K. Restoring degraded face images: A case study in matching faxed, printed, and scanned photos // IEEE Transactions on Information Forensics and Security. – IEEE, 2011. – V. 6. - №2. - P. 371–384.
25. Clark A. D., Whitelam C., Bourlai T. Document to live facial identification // Face Recognition Across the Imaging Spectrum. – Springer, Cham, 2016. – P. 223-245.
26. Li Y., Wang C., Ao X. Illumination processing in face recognition. – InTech, 2010. – P. 187-214.
27. Struc V., Pavesic N. Photometric normalization techniques for illumination invariance // Advances in face image analysis: Techniques and technologies. – IGI Global, 2011. – P. 279-300.
28. Ochoa-Villegas M. A. et al. Addressing the illumination challenge in two-dimensional face recognition: a survey // IET Computer Vision. – 2015. – V. 9. – №. 6. – P. 978-992.
29. Rizzi A., Gatta C., Marini D. A new algorithm for unsupervised global and local color correction // Pattern Recognition Letters. – 2003. – V. 24. – №. 11. – P. 1663-1677.
30. Кобер В. И., Карнаухов В. Н. Адаптивная коррекция неравномерного освещения на цифровых мультиспектральных изображениях // Информационные процессы. – 2016. – Т. 16. – №. 2. – С. 152-161.
31. Гладков А. П., Кузнецова Е. Г., Гладилин С., Грачева М. Адаптивная стабилизация яркости изображения в технической системе распознавания крупных движущихся объектов // Сенсорные системы. — 2017. — Т. 31. — № 3. — С. 247-260.
32. Afifi M., Abdelhamed A. AFIF4: deep gender classification based on adaboost-based fusion of isolated facial features and foggy faces // Journal of Visual Communication and Image Representation. – 2019. – V. 62. – P. 77-86..
33. Phillips P. J. et al. The FERET database and evaluation procedure for face-recognition algorithms // Image and vision computing. – 1998. – V. 16. – №. 5. – P. 295-306.
34. Phillips P. J. et al. The FERET evaluation methodology for face-recognition algorithms //Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. – IEEE, 1997. – P. 137-143.
35. King D. E. Dlib-ml: A machine learning toolkit //Journal of Machine Learning Research. – 2009. – V. 10. №. Jul. – P. 1755-1758.
36. Burger W., Burge M. J. Principles of digital image processing. - Springer, 2009.
37. Ng H.-W., Winkler S. A data-driven approach to cleaning large face datasets // In IEEE International Conference on Image Processing (ICIP’14). - IEEE, 2014. – P. 343–347
38. Yi D. et al. Learning face representation from scratch //arXiv preprint arXiv:1411.7923. – 2014.