Frontiers of Computer Science

, Volume 10, Issue 2, pp 302–316 | Cite as

Max-margin non-negative matrix factorization with flexible spatial constraints based on factor analysis

Research Article
First Online:
Received:
Accepted:
  • 89 Downloads

Abstract

Non-negative matrix factorization (NMF) is a popular feature encoding method for image understanding due to its non-negative properties in representation, but the learnt basis images are not always local due to the lack of explicit constraints in its objective. Various algebraic or geometric local constraints are hence proposed to shape the behaviour of the original NMF. Such constraints are usually rigid in the sense that they have to be specified beforehand instead of learning from the data. In this paper, we propose a flexible spatial constraint method for NMF learning based on factor analysis. Particularly, to learn the local spatial structure of the images, we apply a series of transformations such as orthogonal rotation and thresholding to the factor loading matrix obtained through factor analysis. Then we map the transformed loading matrix into a Laplacian matrix and incorporate this into a max-margin non-negative matrix factorization framework as a penalty term, aiming to learn a representation space which is non-negative, discriminative and localstructure- preserving. We verify the feasibility and effectiveness of the proposed method on several real world datasets with encouraging results.

Keywords

non-negative matrix factorization factor analysis loading matrix flexible spatial constraints 
This is a preview of subscription content, log in to check access.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

11704_2015_4590_MOESM1_ESM.ppt (293 kb)
Supplementary material, approximately 293 KB.

References

  1. 1.
    Bishop C M, Nasrabadi N M. Pattern Recognition and Machine Learning. New York: Springer, 2006MATHGoogle Scholar
  2. 2.
    Turk M, Pentland A. Eigenfaces for recognition. Journal of Cognitive Neuroscience, 1991, 3(1): 71–86CrossRefGoogle Scholar
  3. 3.
    Tipping M E, Bishop C M. Probabilistic principal component analysis. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 1999, 61(3): 611–622MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Zou H, Hastie T, Tibshirani R. Sparse principal component analysis. Journal of Computational and Graphical Statistics, 2006, 15(2): 265–286MathSciNetCrossRefGoogle Scholar
  5. 5.
    Lee D D, Seung H S. Learning the parts of objects by non-negative matrix factorization. Nature, 1999, 401(6755): 788–791CrossRefGoogle Scholar
  6. 6.
    Seung D, Lee L. Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems, 2001, 13: 556–562Google Scholar
  7. 7.
    Ross D A, Zemel R S. Learning parts-based representations of data. The Journal of Machine Learning Research, 2006, 7: 2369–2397MathSciNetMATHGoogle Scholar
  8. 8.
    Lemme A, Reinhart R F, Steil J J. Online learning and generalization of parts-based image representations by non-negative sparse autoencoders. Neural Networks, 2012, 33: 194–203CrossRefGoogle Scholar
  9. 9.
    Wang S, Uchida S, Liwicki M, Feng Y. Part-based methods for handwritten digit recognition. Frontiers of Computer Science, 2013, 7(4): 514–525MathSciNetCrossRefGoogle Scholar
  10. 10.
    Zhang Y, Chen L, Jia J, Zhao Z. Multi-focus image fusion based on non-negative matrix factorization and difference images. Signal Processing, 2014, 105: 84–97CrossRefGoogle Scholar
  11. 11.
    Du H, Hu Q, Zhang X, Hou Y. Image feature extraction via graph embedding regularized projective non-negative matrix factorization. Pattern Recognition, 2014, 483: 196–209Google Scholar
  12. 12.
    Wu Y, Shen B, Ling H. Visual tracking via online nonnegative matrix factorization. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 24(3): 374–383CrossRefGoogle Scholar
  13. 13.
    Wang X, Wang B, Bai X, Liu W, Tu Z. Max-margin multiple-instance dictionary learning. In: Proceedings of the 30th International Conference on Machine Learning. 2013, 846–854Google Scholar
  14. 14.
    Wang Y, Jia Y. Fisher non-negative matrix factorization for learning local features. In: Proceedings of Asian Conference on Computer Vision. 2004Google Scholar
  15. 15.
    Zafeiriou S, Tefas A, Buciu I, Pitas I. Exploiting discriminant information in nonnegative matrix factorization with application to frontal face verification. IEEE Transactions on Neural Networks, 2006, 17(3): 683–695CrossRefGoogle Scholar
  16. 16.
    Li X, Fukui K. Fisher non-negative matrix factorization with pairwise weighting. In: Proceedings of MVA. 2007, 380–383Google Scholar
  17. 17.
    Kotsia I, Zafeiriou S, Pitas I. A novel discriminant non-negative matrix factorization algorithm with applications to facial image characterization problems. IEEE Transactions on Information Forensics and Security, 2007, 2(3): 588–595CrossRefGoogle Scholar
  18. 18.
    Nieto O, Jehan T. Convex non-negative matrix factorization for automatic music structure identification. In: Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. 2013, 236–240CrossRefGoogle Scholar
  19. 19.
    Huang K, Sidiropoulos N D, Swami A. Non-negative matrix factorization revisited: Uniqueness and algorithm for symmetric decomposition. IEEE Transactions on Signal Processing, 2014, 62(1): 211–224MathSciNetCrossRefGoogle Scholar
  20. 20.
    Yanez F, Bach F. Primal-dual algorithms for non-negative matrix factorization with the kullback-leibler divergence. arXiv preprint arXiv:1412.1788, 2014Google Scholar
  21. 21.
    Wang J J Y, Gao X. Max–min distance nonnegative matrix factorization. Neural Networks, 2015, 61: 75–84CrossRefMATHGoogle Scholar
  22. 22.
    Kumar B G, Kotsia I, Patras I. Max-margin non-negative matrix factorization. Image and Vision Computing, 2012, 30(4): 279–291CrossRefGoogle Scholar
  23. 23.
    Kumar B G, Patras I, Kotsia I. Max-margin semi-NMF. In: Proceedings of the 22nd British Machine Vision Conference. 2011Google Scholar
  24. 24.
    Donoho D, Stodden V. When does non-negative matrix factorization give a correct decomposition into parts? In: Proceedings of the Neural Information Processing Systems Conference. 2003, 1141–1148Google Scholar
  25. 25.
    Hoyer P O. Non-negative matrix factorization with sparseness constraints. The Journal of Machine Learning Research, 2004, 5: 1457–1469MathSciNetMATHGoogle Scholar
  26. 26.
    Tan X, Triggs B. Enhanced local texture feature sets for face recognition under difficult lighting conditions. IEEE Transactions on Image Processing, 2010, 19(6): 1635–1650MathSciNetCrossRefGoogle Scholar
  27. 27.
    Wang Y, Liu J, Tang X. Robust 3D face recognition by local shape difference boosting. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(10): 1858–1870CrossRefGoogle Scholar
  28. 28.
    Wang X, Ling H, Xu X. Parts-based face super-resolution via nonnegative matrix factorization. Computers & Electrical Engineering, 2014, 40(8): 130–141CrossRefGoogle Scholar
  29. 29.
    Sharma G, Jurie F, Pérez P. EPML: expanded parts based metric learning for occlusion robust face verification. In: Proceedings of the 12th Asian Conference on Computer Vision. 2014, 1–15Google Scholar
  30. 30.
    Tang Z, Zhang X, Zhang S. Robust perceptual image hashing based on ring partition and nmf. IEEE Transactions on Knowledge and Data Engineering, 2014, 26(3): 711–724CrossRefGoogle Scholar
  31. 31.
    Tian Q, Chen S, Tan X. Comparative study among three strategies of incorporating spatial structures to ordinal image regression. Neurocomputing, 2014, 136: 152–161CrossRefGoogle Scholar
  32. 32.
    Li S Z, Hou X W, Zhang H J, Cheng Q S. Learning spatially localized, parts-based representation. In: Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2001, I–207Google Scholar
  33. 33.
    Jiang B, Zhao H, Tang J, Luo B. A sparse nonnegative matrix factorization technique for graph matching problems. Pattern Recognition, 2014, 47(2): 736–747CrossRefMATHGoogle Scholar
  34. 34.
    Zeng K, Yu J, Li C, You J, Jin T. Image clustering by hyper-graph regularized non-negative matrix factorization. Neurocomputing, 2014, 138: 209–217CrossRefGoogle Scholar
  35. 35.
    Zheng W S, Lai J, Liao S, He R. Extracting non-negative basis images using pixel dispersion penalty. Pattern Recognition, 2012, 45(8): 2912–2926CrossRefGoogle Scholar
  36. 36.
    Chen X, Li C, Cai D. Spatially correlated nonnegative matrix factorization for image analysis. In: Proceedings of the 3rd Sino-foreign interchange Workshop on Intelligent Science and Intelligent Data Engineering. 2012, 148–157Google Scholar
  37. 37.
    Chen X, Li C, Liu H, Cai D. Spatially correlated nonnegative matrix factorization. Neurocomputing, 2014, 139: 15–21CrossRefGoogle Scholar
  38. 38.
    Wu J, Qu W, Hu H, Li Z, Xu Y, Tao Y. A discriminative spatial bagofword scheme with distinct patch. In: Proceedings of the 2014 International Conference on Audio, Language and Image Processing. 2014, 266–271Google Scholar
  39. 39.
    Mu Y, Ding W, Tao D. Local discriminative distance metrics ensemble learning. Pattern Recognition, 2013, 46(8): 2337–2349CrossRefMATHGoogle Scholar
  40. 40.
    Lawton W H, Sylvestre E A. Self modeling curve resolution. Technometrics, 1971, 13(3): 617–633CrossRefGoogle Scholar
  41. 41.
    Paatero P, Tapper U. Positive matrix factorization: A non-negative factor model with optimal utilization of error estimates of data values. Environmetrics, 1994, 5(2): 111–126CrossRefGoogle Scholar
  42. 42.
    Chen X, Tong Z, Liu H, Cai D. Metric learning with two-dimensional smoothness for visual analysis. In: Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition. 2012, 2533–2538CrossRefGoogle Scholar
  43. 43.
    Cai D, He X, Wu X, Han J. Non-negative matrix factorization on manifold. In: Proceedings of the 8th IEEE International Conference on Data Mining. 2008, 63–72Google Scholar
  44. 44.
    Cai D, He X, Han J, Huang T S. Graph regularized nonnegative matrix factorization for data representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(8): 1548–1560CrossRefGoogle Scholar
  45. 45.
    Ando R K, Zhang T. Learning on graph with laplacian regularization. Advances in Neural Information Processing Systems, 2007, 19: 25Google Scholar
  46. 46.
    Fidler S, Skocaj D, Leonardis A. Combining reconstructive and discriminative subspace methods for robust classification and regression by subsampling. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(3): 337–350CrossRefGoogle Scholar
  47. 47.
    Basilevsky A T. Statistical Factor Analysis and Related Methods: Theory and Applications. New York: John Wiley & Sons, 2009MATHGoogle Scholar
  48. 48.
    Martínez A M, Kak A C. PCA versus IDA. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(2): 228–233CrossRefGoogle Scholar
  49. 49.
    Georghiades A S, Belhumeur P N, Kriegman D J. From few to many: illumination cone models for face recognition under variable lighting and pose. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2001, 23(6): 643–660CrossRefGoogle Scholar
  50. 50.
    Hull J J. A database for handwritten text recognition research. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1994, 16(5): 550–554CrossRefGoogle Scholar
  51. 51.
    Schuldt C, Laptev I, Caputo B. Recognizing human actions: a local svm approach. In: Proceedings of the 17th International Conference on Pattern Recognition. 2004, 32–36Google Scholar
  52. 52.
    Hido S, Tsuboi Y, Kashima H, Sugiyama M, Kanamori T. Inlier-based outlier detection via direct density ratio estimation. In: Proceedings of the 8th IEEE International Conference on Data Mining. 2008, 223–232Google Scholar
  53. 53.
    Dalal BN. T. Histograms of oriented gradients for human detection. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2005, 886–893Google Scholar

Copyright information

© Higher Education Press and Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringNanjing University of Aeronautics and AstronauticsNanjingChina

Personalised recommendations