Structure fusion (SF) has been presented for multiple feature fusion via mining the discriminative and complementary information from different feature sets. As the typical methods, SF based on locality preserving projections (SFLPP) and SF based on tensor subspace analysis (SFTSA) have been developed for classification by capturing the complete structure from different features. However, the jointed optimisation function of SFLPP or SFTSA does not clearly explain the modelling mechanism of SF, and its solving process is complex because of iterative eigenvalue decomposition. In this study, structure modelling based on maximisation posterior probability (SMMPP) is proposed for solving these issues. It jointly considers both the certain prior structure (the mutual structure of multiple feature structure described by Ising model) and the uncertain likelihood structure (the possible fusion structure of multiple feature structure represented by Markov random field model) into the framework of Bayes’ rule. The proposed computational solution is faster-converging speed than SFLPP or SFTSA with the guarantee of convergence. Extensive experiments conducted on shape analysis and human action recognition demonstrate the superiority of SMMPP over the state of art methods.

References

1. 1)
  - 24. Shao, L., Jones, S., Li, X.: ‘Efficient search and localization of human actions in video databases’, IEEE Trans. Circuits Syst. Video Technol., 2014, 24, (3), pp. 504–512 (doi: 10.1109/TCSVT.2013.2276700).
2. 2)
  - 13. Yang, X., Yang, X., Zeng, L., et al: ‘Shape classification using contour point sets’, J. Nanjing Univ. Nat. Sci., 2010, 46, (1), pp. 47–55.
3. 3)
  - 11. Karmarkar, N.: ‘A new polynomial-time algorithm for linear programming’. Proc. 16th Annual ACM Symp. on Theory of Computing, 1984, pp. 302–311.
4. 4)
  - 16. Ling, H., Jacobs, D.W.: ‘Shape classification using the inner-distance’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (2), pp. 286–299 (doi: 10.1109/TPAMI.2007.41).
5. 5)
  - 12. Chandrasekaran, S.: ‘An efficient and stable algorithm for the symmetric-definite generalized eigenvalue problem’, SIAM J. Matrix Anal. Appl., 2000, 21, pp. 1202–1228 (doi: 10.1137/S0895479897316308).
6. 6)
  - 19. Wang, J., Bai, X., You, X., et al: ‘Shape matching and classification using height functions’, Pattern Recogn. Lett., 2012, 33, (2), pp. 134–143 (doi: 10.1016/j.patrec.2011.09.042).
7. 7)
  - 7. Li, X., Dai, D., Zhang, X., et al: ‘Structured sparse error coding for face recognition with occlusion’, IEEE Trans. Imag. Proc., 2013, 22, (5), pp. 1889–1900 (doi: 10.1109/TIP.2013.2237920).
8. 8)
  - 18. Yang, X.W., Bai, X., Long in, J.L.: ‘Shape classification based on skeleton path similarity’. The Sixth Int. Conf. on Energy Minimization Methods in Computer Vision and Pattern Recognition, China, 2007, pp. 375–386.
9. 9)
  - 25. Xie, Y., Chang, H., Li, Z., et al: ‘A unified framework for locating and recognizing human actions’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2011, pp. 25–32.
10. 10)
  - 6. Lin, G., Zhu, H., Kang, X., Fan, C., Zhang, E.: ‘Feature structure fusion and its application’, Inf. Fusion, 2014, 20, pp. 146–154 (doi: 10.1016/j.inffus.2014.01.002).
11. 11)
  - 9. Besag, J.: ‘Spatial interaction and the statistical analysis of lattice systems’, J. R. Stat. Soc. B Methodol., 1974, 36, (2), pp. 192–236.
12. 12)
  - 20. Nasreddine, K., Benzinou, A., Fablet, R.: ‘Variational shape matching for shape classification and retrieval’, Pattern Recogn. Lett., 2010, 31, (12), pp. 1650–1657 (doi: 10.1016/j.patrec.2010.05.014).
13. 13)
  - 22. Attalla, E., Siy, P.: ‘Robust shape similarity retrieval based on contour segmentation polygonal multiresolution and elastic matching’, Pattern Recogn., 2005, 38, (12), pp. 2229–2241 (doi: 10.1016/j.patcog.2005.02.009).
14. 14)
  - 8. Lin, G.-F., Zhu, H., Fan, C.-X., Zhang, E.-H.: ‘Human action dynamic modeling recognition based on spatial distribution’, Pattern Recogn. Artif. Intell., 2013, 26, (3), pp. 293–299.
15. 15)
  - 31. Ikizler, N., Duygulu, P.: ‘Histogram of oriented rectangles: a new pose descriptor for human action recognition’, Image Vis. Comput., 2009, 27, (10), pp. 1515–1526 (doi: 10.1016/j.imavis.2009.02.002).
16. 16)
  - 16. Belongie, S., Malik, J., Puzicha, J.: ‘Shape matching and object recognition using shape contexts’, IEEE Trans. Pattern Anal. Mach. Intell., 2002, 24, (4), pp. 509–522 (doi: 10.1109/34.993558).
17. 17)
  - 10. Spitzer, F.: ‘Markov random fields and gibbs ensembles’, Am. Math. Mon., 1971, 78, (2), pp. 142–154 (doi: 10.2307/2317621).
18. 18)
  - 2. Sun, N., Ji, Z., Zou, C., et al: ‘Two-dimensional canonical correlation analysis and its application in small sample size face recognition’, Neural Comput. Appl., 2010, 19, (3), pp. 377–382 (doi: 10.1007/s00521-009-0291-x).
19. 19)
  - 27. Schuldt, C., Laptev, I., Caputo, B.: ‘Recognizing human actions: a local SVM approach’. Proc. 17th Int. Conf. on Pattern Recognition, 2004, vol. 3, pp. 32–36.
20. 20)
  - 23. Liu, L., Shao, L., Rockett, P.: ‘Boosted key-frame selection and correlated pyramidal motion-feature representation for human action recognition’, Pattern Recogn., 2013, 46, (7), pp. 1810–1818 (doi: 10.1016/j.patcog.2012.10.004).
21. 21)
  - 28. Lin, G., Zhu, H., Fan, C., et al: ‘Human action dynamic modeling recognition based on spatial distribution’, Pattern Recogn. Artif. Intell., 2013, 26, (3), pp. 293–299.
22. 22)
  - 4. Xia, T., Tao, D., Mei, T., et al: ‘Multiview spectral embedding’, IEEE Trans. Syst. Man Cybern. B Cybern., 2010, 40, (6), pp. 1438–1446 (doi: 10.1109/TSMCB.2009.2039566).
23. 23)
  - 30. Sun, C., Junejo, I., Foroosh, H.: ‘Action recognition using rank-1 approximation of Joint Self-Similarity Volume’. Proc. IEEE Int. Conf. on Computer Vision (ICCV), 2011, pp. 1007–1012.
24. 24)
  - 1. Sun, T., Chen, S.: ‘Locality preserving CCA with applications to data visualization and pose estimation’, Image Vis. Comput., 2007, 25, (5), pp. 531–543 (doi: 10.1016/j.imavis.2006.04.014).
25. 25)
  - 21. Daliri, M.R., Torre, V.: ‘Robust symbolic representation for shape recognition and retrieval’, Pattern Recogn., 2008, 41, (5), pp. 1782–1798 (doi: 10.1016/j.patcog.2007.10.020).
26. 26)
  - 17. Sun, K.B., Super, B.J.: ‘Classification of contour shapes using class segment sets’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2005, vol. 2, pp. 727–733.
27. 27)
  - 33. Zhen, X., Shao, L., Tao, D., et al: ‘Spatio-temporal laplacian pyramid coding for action recognition’, IEEE Trans. Cybern., 2014, 44, (6), pp. 817–827 (doi: 10.1109/TCYB.2013.2273174).
28. 28)
  - 32. Junejo, I.N., Dexter, E., Laptev, I., et al: ‘View-independent action recognition from temporal self-similarities’, IEEE Trans. Pattern Anal. Mach. Intell., 2011, 33, (1), pp. 172–185 (doi: 10.1109/TPAMI.2010.68).
29. 29)
  - 16. Shu, X., Wu, X.J.: ‘A novel contour descriptor for 2D shape matching and its application to image retrieval’, Image Vis. Comput., 2011, 29, (4), pp. 286–294 (doi: 10.1016/j.imavis.2010.11.001).
30. 30)
  - 29. Kotsia, I., Guo, W., Patras, I.: ‘Higher rank support tensor machines for visual recognition’, Pattern Recogn., 2012, 45, (12), pp. 4192–4203 (doi: 10.1016/j.patcog.2012.04.033).
31. 31)
  - 5. Lin, G., Zhu, H., Kang, X., Fan, C., Zhang, E.: ‘Multi-feature structure fusion of contour for unsupervised shape classification’, Pattern Recogn. Lett., 2013, 34, (11), pp. 1286–1290 (doi: 10.1016/j.patrec.2013.04.011).
32. 32)
  - 3. Sun, B.Y., Zhang, X.M., Li, J., et al: ‘Feature fusion using locally linear embedding for classification’, IEEE Trans. Neural Netw., 2010, 21, (1), pp. 163–168 (doi: 10.1109/TNN.2009.2036363).
33. 33)
  - 26. Gorelick, L., Blank, M., Shechtman, E., et al: ‘Actions as space-time shapes’, IEEE Trans. Pattern Anal. Mach. Intell., 2007, 29, (12), pp. 2247–2253 (doi: 10.1109/TPAMI.2007.70711).

Feature structure fusion modelling for classification

References

Related content