한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제23권6호
  • /
  • Pages.682-689
  • /
  • 2019
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

가려진 얼굴의 인식

Recognition of Occluded Face

  • Kang, Hyunchul (Department of Information and Telecommunication Engineering, Incheon National University)
  • 투고 : 2019.03.15
  • 심사 : 2019.03.31
  • 발행 : 2019.06.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

부분 기반 영상 표현(part-based image representation)에서는 영상의 부분적인 모습을 기저 벡터로 표현하고 기저 벡터의 선형 조합으로 영상을 분해하며, 이 때 기저 벡터의 계수가 곧 물체의 부분적인 특징을 의미하게 된다. 본 논문에는 부분 기반 영상 표현 기법인 비음수 행렬 분해(non-negative matrix factorization, NMF)를 이용하여 얼굴 영상을 표현하고 신경망 기법을 적용하여 가려진 얼굴을 인식하는 얼굴 인식을 제안한다. 표준 비음수 행렬 분해, 투영 경사 비음수 행렬 분해, 직교 비음수 행렬 분해를 이용하여 얼굴 영상을 표현하였고, 각 기법의 성능을 비교하였다. 인식기로는 학습벡터양자화 신경망을 사용하였으며, 인식기에서의 거리 척도로는 유클리디언 거리를 사용하였다. 실험 결과, 전통적인 얼굴 인식 방법에 비하여 제안한 기법이 가려진 얼굴 인식에 보다 강인함을 보인다.

In part-based image representation, the partial shapes of an object are represented as basis vectors, and an image is decomposed as a linear combination of basis vectors where the coefficients of those basis vectors represent the partial (or local) feature of an object. In this paper, a face recognition for occluded faces is proposed in which face images are represented using non-negative matrix factorization(NMF), one of part-based representation techniques, and recognized using an artificial neural network technique. Standard NMF, projected gradient NMF and orthogonal NMF were used in part-based representation of face images, and their performances were compared. Learning vector quantizer were used in the recognizer where Euclidean distance was used as the distance measure. Experimental results show that proposed recognition is more robust than the conventional face recognition for the occluded faces.

키워드

HOJBC0_2019_v23n6_682_f0001.png 이미지

Fig. 1 Face image as a linear combination in NMF.

HOJBC0_2019_v23n6_682_f0002.png 이미지

Fig. 2 Part of basis vectors in S-NMF.

HOJBC0_2019_v23n6_682_f0003.png 이미지

Fig. 3 Part of basis vectors in P-NMF.

HOJBC0_2019_v23n6_682_f0004.png 이미지

Fig. 4 Part of basis vectors in O-NMF.

HOJBC0_2019_v23n6_682_f0005.png 이미지

Fig. 5 Face recognition system using part-based image representation

HOJBC0_2019_v23n6_682_f0006.png 이미지

Fig. 6 Part of ORL image database

HOJBC0_2019_v23n6_682_f0007.png 이미지

Fig. 7 Face image with occlusion (10~60%)

HOJBC0_2019_v23n6_682_f0008.png 이미지

Fig. 8 Average and 150 eigenfaces in PCA

HOJBC0_2019_v23n6_682_f0009.png 이미지

Fig. 9 Recognition rate according to the number of basis vectors

HOJBC0_2019_v23n6_682_f0010.png 이미지

Fig. 10 Recognition rate according to the number of basis vectors with occlusions

Table. 1 Recognition rate according to the number of basis vectors

HOJBC0_2019_v23n6_682_t0001.png 이미지

Table. 2 Recognition rate according to the number of basis vectors with occlusions

HOJBC0_2019_v23n6_682_t0002.png 이미지

참고문헌

  1. R. Abiantu, U. Prabhu, and M. Savvides, "Sparse Feature Extraction for Pose-Tolent Face Recognition," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 36, no. 10, pp. 2061-2073, 2014. https://doi.org/10.1109/TPAMI.2014.2313124
  2. Y. Sun, Y. Chen, X. Wang, and X. Tang, "Deep Learning Face Representation by Joint Identification-Verification," Neural Information Processing Systems, pp. 1988-1996, 2014.
  3. X. Zhu, Z. Lei, J. Yan, D. Yi, and S. Z. Li, "High-Fidelity Pose and Expression Normalization for Face Recognition in the Wild," IEEE Conference on Computer Vision and Pattern Recognition, pp. 787-796, 2015.
  4. S. Zaafeiriou, C. Zhang, and Z. Zhang, "A Survey on face detection in the wild: Past, present and future," Computer Vision and Image Understanding, vol. 138, no. 9, pp.1-24, Sep. 2015. https://doi.org/10.1016/j.cviu.2015.03.015
  5. D. D. Lee, H. S. Seung, "Algorithms for Non-Negative Matrix Factorization," Advances in Neural Information Processing Systems, vol. 13, pp. 556-562, 2001.
  6. D. D. Lee, H. S. Seung, "Learning the Parts of Objects by Non-Negative Matrix Factorization," Nature, vol. 401, no. 6755, pp. 788-791, 1999. https://doi.org/10.1038/44565
  7. J. M. Ban, B. Lee, and H. Kang, "Vehicle Recognition using NMF in Urban Scene," Journal of Korean Information and Communications Society, vol. 37, no. 7, pp. 554-564, 2012. https://doi.org/10.7840/KICS.2012.37.7C.554
  8. J. M. Ban, and H. Kang, "Vehicle Recognition using Non-negative Tensor Factorization," Journal of the Institute of Electronics and Information Engineers, vol. 52, no. 5, pp. 960-970, 2015.
  9. M. Ye, Y. Rian, and J. Zhou, "Multitask sparse nonnegative matrix factorization for joint spectral-spatial hyperspectreal imagery denoising," IEEE Trans. Geoscience and Remote Sensing, vol. 53, no. 5, pp. 2621-2639, 2015. https://doi.org/10.1109/TGRS.2014.2363101
  10. C. Lin, "On the Convergence of Multiplicative Update Algorithms for Nonnegative Matrix Factorization," IEEE Transactions on Neural Networks, vol. 18, no. 6, pp. 1589-1596, 2007. https://doi.org/10.1109/TNN.2007.895831
  11. C. Lin, "Projected Gradient Methods for Nonnegative Matrix Factorization," Neural Computation, vol. 19, no. 10, MIT Press, pp. 2756-2779, 2007. https://doi.org/10.1162/neco.2007.19.10.2756
  12. C. Ding, T. Li, W. Peng, and H. Park, "Orthogonal nonnegative matrix tri-factorizations for clustering," Proceedings of the ACM SIGKDD, pp. 126-135, Philadelphia, PA, 2006.
  13. Y. Wen, K. Zhang, Z. Li, and Y. Qiao, "A Discrminative Feature Learning Approach for Deep Face Recognition," European Conference on Computer Vision, pp. 499-515, 2016.
  14. F. Schroff, D. Kalenichenko, J. Philbin, "FaceNet: A Unified Embedding for Face Recognition and Clustering," IEEE Conference on Computer Vision and Pattern Recognition, pp. 815-823, 2015.
  15. C. Ding, D. Tao, "Robust Face Recognition via Multimodal Deep Face Representation," IEEE Trans. on Multimedia, vol. 17, no. 11, pp. 815-823, Nov. 2015.
  16. T. Kohonen, "The self-organizing map," Proceedings of the IEEE, vol. 78, no. 9, pp. 1464-1480, 1990. https://doi.org/10.1109/5.58325
  17. T. Kohonen, Self-Organization and Associative Memory, 3rd Ed., Springer-Veralg, 2012.
  18. J. H. Choi, and S. Vishwanathan, "DFACTo: Distributed Factorization of Tensors," NIPS, pp. 1296-1304, 2014.