Full Text

Abstract

In this paper an efficient algorithm is presented on the basis of SURF, SVM and MDA. For the detection and description of image features SURF algorithm is used. Firstly the SURF feature detector is applied for the extraction of reference images and for matching the feature points in the image, respectively. In the feature points matching process, false matching points are removed through this algorithm. Here SURF algorithm is used to detect and descript the interest points, and matching the interest points. In this paper, the same is tried to retrieve with the utilization of SURF and then for further classification they are fed into SVM (Support Vector Machine) and MDA (Multi-linear Discriminant Analysis). SURF is fast and robust interest points detector which is used in many computer vision applications. For the implementation of this proposed work we use the Image Processing Toolbox under MATLAB Software.

References

1. B Zitova, J Flusser. Image registration methods: A survey. Image Vis. Comput. 2003; 21(11): 977-1000.

2. Dai X, Khorram S. Development of a Feature-Based Approach to Automated Image Registration for Multi temporal and Multi sensor Remotely Sensed Imagery. Proceedings of the IEEE Interactional Geoscience and Remoth Sensing Symposium. 1997; 1: 243-245.

3. Goshtasby A. Mbolieally-assisted approach to digital image registration with application in computer vision. Ph. D. dissertation, Dept. of Computer Science, Miehigan State University, TR83-013. 1983.

4. Ton J, Jain A. Stering Landsat images by point matehing. IEEE Transactions on Geoscience and Remote Sensing. 1989; 27(5): 642-651.

5. Li H, Manjunath B, Mitra S. Ntour-Based Approach to Multisensor Image Registration. IEEE Transactions on Image Processing. 1995; 4(3): 320-334.

6. Tham J, Ranganath S, Ranganath M, Kassim A. Vel Unrestricted Center-Biased Diamond Search Algorithm for Block Motion Estimation. IEEE Transactions on Circuits System and Video Technology. 1998; 8(4): 369-377.

7. Yuan Z, Wu F, Zhuang Y. I-sensor image registration using multi-resolution shape analysis. Journal Of Zhejiang University Science A. 2006; (4): 549-555.

8. Ziou D, Tabbone S. Dtection techniques-an overview. International Journal of Pattern Recognition and Image Analysis. 1988; (5): 537-559.

9. Mount D, Netanyahu N, Moigne J. Ent Algorithms for Robust Feature Matching. Pattern Recognition, 1999; 32(1): 17-38.

10. Bay H, Tuvtellars T, Gool L Van. SURF: speeded up robust features. Proceedings of the European Conference on Computer Vision. 2006: 404 417.

11. Rong W, Chen H, et al. Icing of Microscope Images based on SURF. 24th International Conference Image and Vision Computing New Zealand (IVCNZ2009). 2009: 272-275.

12. Hartley R, Zisserman A. View Geometry in Computer Vision, second. ed. Cambridge University Press, Cambridge. 2003.

13. Tola E, Lepetit V. St local descriptor for dense matching. IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, DC: IEEE Computer Society. 2008: 1-8.

14. Tola E, Lepetit VY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo. IEEE Transactions on Pattern Analysis & Machine Intelligence. 2010; 32(5): 815-830.

15. Bracewell R. Fourier Transform and Its Applications. McGraw-Hill, New York. 1965.

16. Xiaoli Li, Xiaohong Wang and Chunsheng Li: Image Matching Based on Unification, The Fourth International Joint Conference on Computational Science and Optimization (2011), p. 825-828.

17. Herbert Bay, Andreas Ess, Tinne Tuytelaars and Luc Van Gool: Speeded-Up Robust Features (SURF), Computer Vision and Image Understanding (2008), 110(3), p. 346-359.

18. David G. Lowe: Distinctive Image Features from Scale-Invariant Keypoints, International Journal of Computer Vision (2004), 60(2), p. 91-110.

19. Luo Juan and Oubong Gwun: A Comparison of SIFT, PCA-SIFT and SURF, International Journal of Image Processing (2009), 3(4), p. 143-152.

20. Dorigo M., Maniezzo V. and Colorni A.: Ant System: Optimization by A Colony of Cooperating Agents, IEEE Transaction on Systems, Man, and Cybernetics-Part B (1996), 26(1), p. 29-41.

Keywords

CBIR, SURF, Support Vector Machine, MDA, classification, interest point