On the basis of feature points pairing, a scale-invariant feature matching method is proposed in this study. The distance between two features is used to compute feature pairs' support region size, which is different from the methods using detectors to provide information to find the support region. Moreover, to achieve rotation invariance, a sub-region division method based on intensity order is introduced. For comparison to the popular descriptors scale-invariant feature transform and speeded-up robust features, the authors also choose the detected points by difference of Gaussian and fast Hessain detectors as feature points to start the authors' method. Additional experiments compare the reported method with similar proposed methods, such as Tell's and Fan's. The experimental results show that the authors' proposed descriptor outperforms the popular descriptors under various image transformations, especially on images with scale and viewpoint transformations.

References

1. 1)
  - 2. Hoang, T.V., Tabbone, S.: ‘Invariant pattern recognition using the RFM descriptor’, Pattern Recogn., 2012, 45, (1), pp. 271–284 (doi: 10.1016/j.patcog.2011.06.020).
2. 2)
  - 25. Fergus, R., Perona, P., Zisserman, A.: ‘Object class recognition by unsupervised scale-invariant learning’. IEEE Conf. Computer Vision and Pattern Recognition, Madison, America, 2003, pp. 264–271.
3. 3)
  - 15. Lindeberg, T., Garding, J.: ‘Shape-adapted smoothing in estimation of 3D depth cues from affine distortions of local 2D brightness structure’. Eur. Conf. Comput. Vision, Stockholm, Sweden, 1994, pp. 389–400.
4. 4)
  - 26. Pedro, F.F., Ross, B.G., David, M., et al: ‘Object detection with discriminatively trained part-based models’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (9), pp. 1627–1645 (doi: 10.1109/TPAMI.2009.167).
5. 5)
  - 19. Dorkó, G., Schmid, C.: ‘Maximally stable local description for scale selection’. Eur. Conf. Comput. Vision, Graz, Austria, 2006, pp. 504–516.
6. 6)
  - 8. Fan, B., Wu, F.C., Hu, Z.Y.: ‘Aggregating gradient distributions into intensity orders: A novel local image descriptor’. IEEE Conf. Computer Vision and Pattern Recognition, Providence, Rhode Island, 2011, pp. 2377–2384.
7. 7)
  - 16. Kadir, T., Brady, M.: ‘Saliency, scale and image description’, Int. J. Comput. Vis., 2001, 45, (2), pp. 83–105 (doi: 10.1023/A:1012460413855).
8. 8)
  - 6. Bay, H., Ess, A., Tuytelaars, T., et al: ‘SURF: Speeded up robust features’, Comput. Vis. Image Underst., 2008, 110, (3), pp. 346–359 (doi: 10.1016/j.cviu.2007.09.014).
9. 9)
  - 3. Li, J.Y., Wang, Y.L., Wang, Y.J.: ‘Visual tracking and learning using speeded up robust features’, Pattern Recogn., 2012, 33, (16), pp. 2094–2101 (doi: 10.1016/j.patrec.2012.08.002).
10. 10)
  - 7. Tola, E., Lepetit, V., Fua, P.: ‘An efficient dense descriptor applied to wide-baseline stereo’, IEEE Trans. Pattern Anal. Mach. Intell., 2010, 32, (5), pp. 815–830 (doi: 10.1109/TPAMI.2009.77).
11. 11)
  - 18. Okada, K., Comaniciu, D., Krishnan, A.: ‘Scale selection for anisotropic scale-space: application to volumetric tumor characterization’. IEEE Conf. Computer Vision and Pattern Recognition, Washington DC, America, 2004, pp. 594–601.
12. 12)
  - 28. Mikolajczyk, K., Schmid, C.: ‘A performance evaluation of local descriptors’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (10), pp. 1615–1630 (doi: 10.1109/TPAMI.2005.188).
13. 13)
  - 23. Tell, D., Carlsson, S.: ‘Wide baseline point matching using affine invariants computed from intensity profiles’. Eur. Conf. Comput. Vision, Dublin, Ireland, 2000, pp. 814–828.
14. 14)
  - 22. Jafari-Khouzani, K., Soltanian-Zadeh, H.: ‘Radon transform orientation estimation for rotation invariant texture analysis’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (6), pp. 1004–1008 (doi: 10.1109/TPAMI.2005.126).
15. 15)
  - 12. Witkin, A., Terzopoulos, D., Kass, M.: ‘Signal matching through scale space’, Int. J. Comput. Vis., 1987, 1, (2), pp. 133–144 (doi: 10.1007/BF00123162).
16. 16)
  - 22. Ojala, T., Pietikainen, M., Maenpaa, T.: ‘Multiresolution gray-scale and rotation invariant texture classification with local binary patterns’, Trans. Pattern Anal. Mach. Intell., 2002, 24, (7), pp. 971–987 (doi: 10.1109/TPAMI.2002.1017623).
17. 17)
  - 10. Fan, B., Wu, F.C., Hu, Z.Y.: ‘Rotationally invariant descriptors using intensity order pooling’, IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, (10), pp. 2031–2045 (doi: 10.1109/TPAMI.2011.277).
18. 18)
  - 20. Lazebnik, S., Schmid, C., Ponce, J.: ‘A sparse texture representation using local affine regions’, IEEE Trans. Pattern Anal. Mach. Intell., 2005, 27, (8), pp. 1265–1278 (doi: 10.1109/TPAMI.2005.151).
19. 19)
  - 1. Michel, D., Oikonomidis, I., Argyros, A.: ‘Scale invariant and deformation tolerant partial shape matching’, Image Vis. Comput., 2011, 29, (7), pp. 459–469 (doi: 10.1016/j.imavis.2011.01.008).
20. 20)
  - 4. Tolias, G., Kalantidis, Y., Avrithis, Y., et al: ‘Towards large-scale geometry indexing by feature selection’, Comput. Vis. Image Underst., 2014, 120, pp. 31–45 (doi: 10.1016/j.cviu.2013.12.002).
21. 21)
  - 9. Wang, Z.H., Fan, B., Wu, F.C.: ‘Local intensity order pattern for feature description’. Int. Conf. Comput. Vis., Barcelona, Spain, 2011, pp. 603–610.
22. 22)
  - 24. Fan, B., Wu, F.C., Hu, Z.Y.: ‘Towards reliable matching of images containing repetitive patterns’, Pattern Recogn. Lett., 2011, 32, (14), pp. 1851–1859 (doi: 10.1016/j.patrec.2011.07.029).
23. 23)
  - 11. Lindeberg, T.: ‘Scale-space for discrete signals’, IEEE Trans. Pattern Anal. Mach. Intell., 1990, 12, (3), pp. 234–254 (doi: 10.1109/34.49051).
24. 24)
  - 17. Dufournaud, Y., Schmid, C., Horaud, R.: ‘Image matching with scale adjustment’, Comput. Vis. Image Underst., 2004, 93, (2), pp. 175–194 (doi: 10.1016/j.cviu.2003.07.003).
25. 25)
  - 14. Harris, C., Stephens, M.: ‘A combined corner and edge detector’. Proc. Fourth Alvey Vision Conf., Manchester, England, 1998, pp. 147–151.
26. 26)
  - 13. Mikolajczyk, K., Schmid, C.: ‘Scale and affine invariant interest point detectors’, Int. J. Comput. Vis., 2004, 60, (1), pp. 63–86 (doi: 10.1023/B:VISI.0000027790.02288.f2).
27. 27)
  - 20. Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, Int. J. Comput. Vis., 2004, 60, pp. 91–110 (doi: 10.1023/B:VISI.0000029664.99615.94).
28. 28)
  - 27. Wu, F.C., Wang, Z.H., Wang, X.G.: ‘Feature vector field and feature matching’, Pattern Recogn., 2010, 43, (10), pp. 3273–3281 (doi: 10.1016/j.patcog.2010.05.001).

Scale-invariant feature matching based on pairs of feature points

References

Related content