Journal of Digital Contents Society (디지털콘텐츠학회 논문지)

Digital Contents Society (한국디지털콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Face Recognition via Sparse Representation using the ROMP Method

ROMP를 이용한 희소 표현 방식 얼굴 인식 방법론

  • Ahn, Jung-Ho (Division of Software Application, Kangnam University) ;
  • Choi, KwonTaeg (Division of Software Application, Kangnam University)
  • 안정호 (강남대학교 소프트웨어응용학부 가상현실전공) ;
  • 최권택 (강남대학교 소프트웨어응용학부 가상현실전공)
  • Received : 2017.03.13
  • Accepted : 2017.04.25
  • Published : 2017.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

It is well-known that the face recognition method via sparse representation has been proved very robust and showed good performance. Its weakness is, however, that its time complexity is very high because it should solve $L_1$-minimization problem to find the sparse solution. In this paper, we propose to use the ROMP(Regularized Orthogonal Matching Pursuit) method for the sparse solution, which solves the $L_2$-minimization problem with regularization condition using the greed strategy. In experiments, we shows that the proposed method is comparable to the existing best $L_1$-minimization solver, Homotopy, but is 60 times faster than Homotopy. Also, we proposed C-SCI method for classification. The C-SCI method is very effective since it considers the sparse solution only without reconstructing the test data. It is shown that the C-SCI method is comparable to, but is 5 times faster than the existing best classification method.

희소 표현을 이용한 얼굴 인식 방법론은 강인성이 입증된 우수한 얼굴 인식 방법으로 알려져 있다. 이 방법론의 단점은 $L_1$-노름 최적화 문제를 통해 희소해를 구하는 과정에서 많은 시간이 소요되어 실시간 응용 분야에 적합하지 않다는 것이다. 통상적인 $L_2$-노름 최적화 문제를 통해 얻어진 희소해는 희소성이 결여되고 정확도가 떨어져서 희소 표현을 이용한 인식 방법론에는 사용되고 있지 않다. 우리는 본 논문에서는 탐욕적인 방식으로 $L_2$-노름 최적화 문제를 푸는 ROMP 방식을 도입해 희소해를 구하는 방법을 제안하고, 실험을 통해 제안한 방식이 정확도에서 기존 방식과 유사하며 속도는 60배 이상 빠름을 보였다. 또한, 희소 표현기반인식 방법론으로 희소해의 분포만을 고려하여 분류하는 단순한 방식인 C-SCI 방법론을 제안하였다. 이 방법론은 테스트 데이터를 복원하는 기존 방식과 성능 면에서는 유사하나 속도 면에서는 약 5배 빠름을 실험적으로 입증하였고, 이론적인 복잡도 분석 결과도 제시하였다.

Keywords

References

  1. Y. Sun, X. Wang and X. Tang, "Deep learning face representation from predicting 10,000 classes", in Proceeding of 2015 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1891-1898, June 2014.
  2. Y. Sun, X. Wang and X. Tang, "Robust face recognition via multimodal deep face representation", IEEE transactions on Multimedia, Vol. 17, No. 11, pp. 2049-2058, September 2015. https://doi.org/10.1109/TMM.2015.2477042
  3. A. T. Tran, R. Hassner, I. Masi and G. Medioni, "Regressing robust and discriminative 3D morphable models with a very deep neural network", arXiv preprint arXiv:1612.04904, 15. December, 2016.
  4. J. Wright, A. Y. Yang, A. Ganesh, S. S. Sastry and Y. Ma, "Robust face recognition via sparse representation", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 2, pp. 210-227, February 2009. https://doi.org/10.1109/TPAMI.2008.79
  5. A. Yang, S. Sastry, A. Ganesh and Y. Ma, "Fast L1-minimization algorithms and an application in robust face recognition: A review", in Proceeding of International Conference on Image Processing, pp. 471-478, October 2010.
  6. L. Zhang, M. Yang and X. Feng, "Sparse representation or collaborative representation: Which helps face recognition?", in Proceeding of ICCV'11 International Conference on Computer Vision, pp. 471-478, November 2011.
  7. T. Guha and R. W. Ward, "Learning Sparse Representations for Human Action Recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 34, No. 8, pp. 1576-1588, August 2012. https://doi.org/10.1109/TPAMI.2011.253
  8. J. Wang, C. Lu and M. Wang, "Robust face recognition via adaptive sparse representation", IEEE Transactions on Cybernetics, Vol. 44, No. 12, pp. 2368-2378, December 2014. https://doi.org/10.1109/TCYB.2014.2307067
  9. Z. Fan, M. Ni, Q. Zhu and E. Liu, "Weighted sparse representation for face recognition", Neurocomputing, Vol. 151, No. 1, pp. 304-309, March 2015. https://doi.org/10.1016/j.neucom.2014.09.035
  10. Z. Zhang, Y. Liang, L. Bai and E. R. Hancock, "Discriminative sparse representation for face recognition", Multimedia Tools and Applications, Vol. 75, No. 7, pp. 3973-3992, April 2016. https://doi.org/10.1007/s11042-015-3136-x
  11. E. J. Candes and M. B. Wakin, "An Introduction to compressive sampling", IEEE Signal Precessing Magazine, Vol. 25, No. 2, pp. 21-30, March 2009.
  12. V. Temlyakov, "Nonlinear methods of approximation", Foundations of Computational Mathematics, Vol. 3, No. 1, pp. 33-107, January 2003. https://doi.org/10.1007/s102080010029
  13. T. Blumensath and M. E. Davies, "Gradient Pursuits", IEEE Transactions on Signal Processing, Vol. 56, No. 6, pp. 2370-2382, May 2008. https://doi.org/10.1109/TSP.2007.916124
  14. D. Needell and R. Vershynin, "Uniform uncertainty principle and signal recovery via regularized orthogonal matching pursuit", Foundations of Computational Mathematics, Vol. 9, No. 3, pp. 317-334, June 2009. https://doi.org/10.1007/s10208-008-9031-3
  15. T. Ojala, M. Pietikainen and T. Maenpaa, "Multiresolution gray-scale and rotation invariant texture classification with local binary patterns", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 24, No. 7, pp. 971-987, July 2002. https://doi.org/10.1109/TPAMI.2002.1017623
  16. T. Ahonen, A. Hadid and M. Pietikainen, "Face description with local binary patterns: Application to face recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 28, No. 12, pp. 2037-2041, December 2006. https://doi.org/10.1109/TPAMI.2006.244
  17. P. N. Belhumeur, J.P. Hespanha and D. J. Kriegman, "Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 19, No. 7, pp. 711-720, July 1997. https://doi.org/10.1109/34.598228
  18. J.-M. Kim and K.-J. Lee, "Real Time Face Detection and Recognition using Rectangular Feature Based Classifier and PCA-based MLNN", Journal of Digital Contents Society, Vol. 11, No. 4, pp. 417-424, December 2010.