© The Institution of Engineering and Technology
This study presents a local image descriptor based on spectral embedding. Specifically, the spectra of line graph are used to represent image edges, corners and edge points with big curvature. The authors theoretically analyse and experimentally verify that the spectra of line graph are robust to noise and are invariant to rotation and linear intensity changes. Based on such a fact, some local image descriptors are constructed using the spectra of line graph. Comparative experiments demonstrate the effectiveness of the proposed descriptor and its superiority to some state-of-the-art descriptors under image rotation, image blur, viewpoint change, illumination change, JPEG compression and noise.
References
-
-
1)
-
J. Shi ,
J. Malik
.
Normalized cuts and image segmentation.
IEEE Trans. Pattern Anal. Mach. Intel.
,
8 ,
888 -
905
-
2)
-
21. Duanduan, Y., Sluzek, A.: ‘A low-dimensional local descriptor incorporating TPS warping for image matching’, Image Vis. Comput., 2010, 28, (8), pp. 1184–1195 (doi: 10.1016/j.imavis.2009.12.003).
-
3)
-
9. Lv, Q., Fang, S., Zhang, Z.: ‘Feature points extraction of different structure for industrial computed tomography image contour’, Optik-Int. J. Light Electron Opt., 2013, 124, (22), pp. 5313–5317 (doi: 10.1016/j.ijleo.2013.03.163).
-
4)
-
31. Carcassoni, M., Hancock, E.R.: ‘Spectral correspondence for point pattern matching’, Pattern Recognit., 2003, 36, (1), pp. 193–204 (doi: 10.1016/S0031-3203(02)00054-7).
-
5)
-
40. Brouwer, A.E., Haemers, W.H.: ‘Spectra of graphs’ (Springer Press, 2012).
-
6)
-
H. Bay ,
A. Ess ,
T. Tuytelaars ,
L.V. Gool
.
SURF: speeded up robust features.
Comput. Vis. Image Underst.
,
3 ,
346 -
359
-
7)
-
33. Bansal, M., Daniilidis, K.: ‘Joint spectral correspondence for disparate image matching’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Portland, OR, USA, June 2013, pp. 2802–2809.
-
8)
-
32. Tang, J., Liang, D., Wang, N., Fan, Y.Z.: ‘A Laplacian spectral method for stereo correspondence’, Pattern Recognit. Lett., 2007, 28, (12), pp. 1391–1399 (doi: 10.1016/j.patrec.2007.01.020).
-
9)
-
25. Ding, C.H.Q., He, X.F., Zha, H.Y., Gu, M., Simon, H.D.: ‘A min-max cut algorithm for graph partitioning and data clustering’. Proc. IEEE Int. Conf. on Data Mining, San Jose, CA, USA, November 2001, pp. 107–114.
-
10)
-
S. Belongie ,
J. Malik ,
J. Puzicha
.
Shape matching and object recognition using shape contexts.
IEEE Trans. Pattern Anal. Mach. Intell.
,
4 ,
509 -
522
-
11)
-
Y. Furukawa ,
J. Ponce
.
Accurate, dense, and robust multi-view stereopsis.
Pattern Anal. Mach. Intell.
,
8 ,
1362 -
1376
-
12)
-
13)
-
6. Yang, Y., Newsam, S.: ‘Geographic image retrieval using local invariant features’, IEEE Trans. Geosci. Remote Sens., 2013, 51, (2), pp. 818–832 (doi: 10.1109/TGRS.2012.2205158).
-
14)
-
30. Shapiro, L.S., Brady, J.M.: ‘Feature-based correspondence: an eigenvector approach’, Image Vis. Comput., 1992, 10, (5), pp. 283–288 (doi: 10.1016/0262-8856(92)90043-3).
-
15)
-
17. Wang, Z.H., Fan, B., Wu, F.C.: ‘Local intensity order pattern for feature description’. Proc. IEEE Int. Conf. Computer Vision, Barcelona, Spain, November 2011, pp. 603–610.
-
16)
-
5. Grady, L., Schwartz, E.: ‘Isoperimetric graph partitioning for image segmentation’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (3), pp. 469–475 (doi: 10.1109/TPAMI.2006.57).
-
17)
-
18)
-
15. Matas, J., Chum, O., Martin, U., Pajdla, T.: ‘Robust wide baseline stereo from maximally stable extremal regions’. Proc. 13th British Machine Vision Conf., Cardiff, UK, September 2002, pp. 384–393.
-
19)
-
36. Zhang, X.Q., Hu, W.M., Chen, S.Y., Maybank, S.: ‘Graph-embedding-based learning for robust object tracking’, IEEE Trans. Ind. Electron., 2014, 61, (2), pp. 1072–1084 (doi: 10.1109/TIE.2013.2258306).
-
20)
-
34. Tang, J., Zhang, C.Y., Luo, B.: ‘A graph and PNN-based approach to image classification’. Proc. Fourth Int. Conf. on Machine Learning and Cybernetics, Guangzhou, China, August 2005, pp. 18–21.
-
21)
-
K. Mikolajczyk ,
C. Schmid
.
A performance evaluation of local descriptors.
IEEE Trans. Pattern Anal. Mach. Intell.
,
10 ,
1615 -
1629
-
22)
-
7. Wang, S.H., You, H.J., Fu, K.: ‘BFSIFT: a novel method to find feature matches for SAR image registration’, IEEE Geosci. Remote Sens. Lett., 2012, 9, (4), pp. 649–653 (doi: 10.1109/LGRS.2011.2177437).
-
23)
-
12. Stottinger, J., Hanbury, A., Sebe, N., Gevers, T.: ‘Sparse color interest points for image retrieval and object categorization’, IEEE Trans. Image Process., 2012, 21, (5), pp. 2681–2692 (doi: 10.1109/TIP.2012.2186143).
-
24)
-
D.G. Lowe
.
Distinctive image features from scale-invariant keypoints.
Int. J. Comput. Vis
,
2 ,
91 -
110
-
25)
-
29. Scott, G.L., Longuet-Higgins, H.C.: ‘An algorithm for associating the features of two images’. Proc. Roy. Soc. Lond., London, UK, 1991, pp. 21–26.
-
26)
-
K. Mikolajczyk ,
C. Schmid
.
Scale & affine invariant interest point detectors.
Int. J. Comput. Vis.
,
1 ,
63 -
86
-
27)
-
25. Wang, S., Siskind, J.M.: ‘Image segmentation with ratio cut’, IEEE Trans. Pattern Anal. Mach. Intell., 2003, 25, pp. 675–690 (doi: 10.1109/TPAMI.2003.1201819).
-
28)
-
28. Veksler, O.: ‘Image segmentation by nested cuts’. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, SC, USA, June 2000, pp. 339–344.
-
29)
-
22. Li, C., Ma, L.: ‘A new framework for feature descriptor based on SIFT’, Pattern Recognit. Lett., 2009, 30, (5), pp. 544–557 (doi: 10.1016/j.patrec.2008.12.004).
-
30)
-
1. Zhao, W.L., Ngo, C.W.: ‘Flip-invariant SIFT for copy and object detection’, IEEE Trans. Image Process., 2013, 22, (3), pp. 980–991 (doi: 10.1109/TIP.2012.2226043).
-
31)
-
22. Wu, F.C., Wang, Z.H., Wang, X.G.: ‘Feature vector field and feature matching’, Pattern Recognit., 2010, 43, (10), pp. 3273–3281 (doi: 10.1016/j.patcog.2010.05.001).
-
32)
-
5. Qian, X.M., Hua, X.S., Chen, P., Ke, L.J.: ‘PLBP: an effective local binary patterns texture descriptor with pyramid representation’, Pattern Recognit., 2011, 44, (10/11), pp. 2502–2515 (doi: 10.1016/j.patcog.2011.03.029).
-
33)
-
35. Sussman, D.L., Minh, T., Priebe, C.E.: ‘Consistent latent position estimation and vertex classification for random dot product graphs’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, (1), pp. 48–57 (doi: 10.1109/TPAMI.2013.135).
-
34)
-
J. Zhang ,
M. Marszalek ,
S. Lazebnik ,
C. Schmid
.
Local features and kernels for classification of texture and object categories: a comprehensive study.
Int. J. Comput. Vis.
,
2 ,
213 -
238
-
35)
-
37. Zhang, L.M., Han, Y.H., Yang, Y., et al: ‘Discovering discriminative graphlets for aerial image categories recognition’, IEEE Trans. Image Process., 2013, 22, (12), pp. 5071–5084 (doi: 10.1109/TIP.2013.2278465).
-
36)
-
8. Fathima, A.A., Karthik, R., Vaidehi, V.: ‘Image stitching with combined moment invariants and sift features’, Proc. Comp. Sci., 2013, 19, pp. 420–427 (doi: 10.1016/j.procs.2013.06.057).
-
37)
-
13. Kanehisa, M., Goto, S., Hattori, M., et al: ‘From genomics to chemical genomics: new developments in kegg’, Nucleic Acids Res., 2006, 35, pp. 354–357 (doi: 10.1093/nar/gkj102).
-
38)
-
10. Harris, C., Stephens, M.: ‘A combined corner and edge detection’. Proc. 4th Alvey Vision Conf., Manchester, UK, August 1988, pp. 147–152.
-
39)
-
T. Lindeberg
.
Detecting salient blob-like image structures and their scales with a scale-space primal sketch: a method for focus of attention.
Int. J. Comput. Vis.
,
3 ,
283 -
318
-
40)
-
Z.Y. Wu ,
R. Leahy
.
An optimal graph theoretic approach to data clustering: theory and its application to image segmentation.
IEEE Trans. Pattern Anal. Mach. Intell.
,
11 ,
1101 -
1113
-
41)
-
42)
-
K. Mikolajczyk ,
T. Tuytelaars ,
C. Schmid ,
A. Zisserman ,
J. Matas ,
F. Schaffslatzky ,
T. Kadir ,
V.L. Gool
.
A comparison of affine region detectors.
Int. J. Comput. Vis.
,
1 ,
43 -
72
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2014.0124
Related content
content/journals/10.1049/iet-cvi.2014.0124
pub_keyword,iet_inspecKeyword,pub_concept
6
6