DOI QR코드

DOI QR Code

개인별 주요 블록의 다중 반경 LBP 매칭을 이용한 모바일 환경에서의 얼굴인증

Face Authentication using Multi-radius LBP Matching of Individual Major Blocks in Mobile Environment

  • 이정섭 (경희대학교 컴퓨터공학과) ;
  • 안희석 (경희대학교 컴퓨터공학과) ;
  • 금지수 (경희대학교 컴퓨터공학과) ;
  • 김태형 (경희대학교 컴퓨터공학과) ;
  • 이승형 (경희대학교 컴퓨터공학과) ;
  • 이현수 (경희대학교 컴퓨터공학과)
  • Lee, Jeong-Sub (Department of Computer Engineering, Kyung Hee University) ;
  • Ahn, Hee-Seok (Department of Computer Engineering, Kyung Hee University) ;
  • Keum, Ji-Soo (Department of Computer Engineering, Kyung Hee University) ;
  • Kim, Tai-Hyung (Department of Computer Engineering, Kyung Hee University) ;
  • Lee, Seung-Hyung (Department of Computer Engineering, Kyung Hee University) ;
  • Lee, Hyon-Soo (Department of Computer Engineering, Kyung Hee University)
  • 투고 : 2013.05.13
  • 심사 : 2013.07.24
  • 발행 : 2013.07.30

초록

본 논문에서는 모바일 환경에서의 얼굴인증을 위해 개인별 주요 블록에 대한 LBP 매칭 기반의 새로운 방법을 제안한다. 주어진 사진으로부터 개인별 주요 블록을 구성하기 위하여 유사도가 높은 블록을 찾아 블록별 확률 분포를 계산하고 임계값을 적용하여 사람마다 다른 블록의 개수를 얼굴인증에 사용하도록 한다. 그리고 단일 반경 LBP 기반 얼굴인증 방법의 성능 향상을 위하여 다중 반경 LBP 히스토그램을 이용하여 개인별 주요 블록을 결정한다. 실험 결과 다중 반경 LBP 히스토그램을 이용함으로써 단일 반경 LBP 히스토그램만 사용하여 얼굴인증을 수행할 때보다 타인의 인증을 수락하는 오인수락율을 줄일 수 있었다. 또한, 기존 방법과의 성능 비교에서 제안한 방법이 블록의 개수는 기존 방법의 44.59%만 사용하면서 인증 오류율은 평균 7.72% 낮은 결과를 얻었다.

In this paper, we propose a novel face authentication method based on LBP matching of individual major blocks in mobile environment. In order to construct individual major blocks from photos, we find the blocks that have the highest similarity and use different numbers of blocks depending on the probability distribution by applying threshold. And, we use multi-radius LBP histograms in the determination of individual major blocks to improve performance of generic LBP histogram based approach. By using the multi-radius LBP histograms in face authentication, we can successfully reduce the false acceptance rate compare to the previous methods. Also, we can see that the proposed method shows low error rate about 7.72% compare to the pervious method in spite of use small number of blocks about 44.59% only.

키워드

참고문헌

  1. M.A. Turk and A.P. Pentland, "Face recognition using eigenfaces," Proc. Int. Conf. on Computer Vision and Pattern Recognition, pp.586-591, 1991.
  2. K. Etemad and R. Chellappa, "Discriminant analysis for recognition of human face images," Journal of Optical Society of America A, vol.14, no.8, pp.1724-1733, 1997. https://doi.org/10.1364/JOSAA.14.001724
  3. G. Donato, M.S. Bartlett, J.C. Hager, P. Ekman, and T.J. Sejnowski, "Classifying facial actions," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.21, no.10, pp.974-989, 1999. https://doi.org/10.1109/34.799905
  4. D.G. Lowe, "Distinctive image features from scale-invariant keypoints," International Journal of Computer Vision, vol.60, no.2, pp.91-110, 2004. https://doi.org/10.1023/B:VISI.0000029664.99615.94
  5. D. Ozkan and P.I. Duygulu, "Interesting faces: A graph-based approach for finding people in news," Pattern Recognition, vol.43, no.5, pp.1717-1735, 2010. https://doi.org/10.1016/j.patcog.2009.10.015
  6. T. Ojala, M. Pietikainen, and T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol.24, no.7, pp.971-987, 2002. https://doi.org/10.1109/TPAMI.2002.1017623
  7. T. Ahonen, A. Hadid, and M. Pietikainen, "Face recognition with local binary patterns," Proc. European Conf. on Computer Vision, pp.469-481, 2004.
  8. Y. Rodriguez and S. Marcel, "Face authentication using adapted local binary pattern histograms," Proc. European Conf. on Computer Vision, pp.321-332, 2006.
  9. C. Shan and T. Gritti, "Learning discriminative LBP-histogram bins for facial expression recognition," Proc. British Machine Vision Conf., 2008.
  10. S. Yan, H. Wang, X. Tang, and T. Haung, "Exploring feature descriptors for face recognition," Proc. Int. Conf. on Acoustics, Speech and Signal Processing, pp.629-632, 2007.
  11. C.-H. Chan, J. Kittler, and K. Messer, "Multi-scale local binary pattern histograms for face recognition," Proc. Int. Conf. on Biometrics, pp.809-818, 2007.
  12. J. Lee and D. Kim "Face recognition method using LBP and Top-N block matching," Proc. Korea Computer Congress, vol.38, no.1(B), pp.300-301, 2011.
  13. D-J. Kim, M-K. Sohn, and S-H. Lee "A study on face recognition method based on binary pattern image under varying lighting condition," The Institute of Electronics Engineers of Korea - Computer and Information, vol.49, no.2, pp.114-127, 2012.
  14. D. Huang, C. Shan, M. Ardabilian, Y. Wang, and L. Chen, "Local binary patterns and its application to facial image analysis: a survey," IEEE Trans. on Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol.41, no.6, pp.765-781, 2011. https://doi.org/10.1109/TSMCC.2011.2118750
  15. T-H. Kim, J-S. Lee, H-S. Ahn, K-J. Kim, J-S. Keum, S-H. Lee, and H-S. Lee, "Face authentication using LBP matching of individual major blocks in mobile environment," Proc. Workshop on Image Processing and Image Understanding (IPIU), 2013.
  16. Caltech Faces 1999 Database - http://www.vision.caltech.edu/Image_ Datasets/faces/