Image Matching Application Based on Modified SURF Algorithm

Abstract:

The key technique to increase the accuracy of electronic marking is the technique of image matching, namely to match two doubtfully duplicate images. Currently there are few technologies aiming for features on test paper images with high performance on matching accuracy. The research is based on SURF algorithm and specific to the features of test paper images. Thus the research is to put forward the modified algorithm with constraints among feature spots of orientation angles on their geometrical positions, including differential constraints on critical points from approximate blank test papers with less individual features at the same time. After processing and analyzing 2,000 test paper gathered from one actual examination, the results show that the modified detection algorithm has 100% false rejection rate and 100% accuracy when it is used to detect the test paper matching.

• Periodical: Applied Mechanics and Materials (Volumes 423-426)
• Pages: 2591-2596
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.423-426.2591
• Online since: September 2013
• Authors: Zhen Yuan Ma*, Shi Xu Shi, Li Xian Yuan, Pei Chang Gu, Han Huang
• Keywords: Electronic Marking, Geometric Constraint, Image Matching, SURF

References

[1] H. Bay, T. van Tuytelaars: Gool Speeded-up Robust Features(SURF) (Computer Vision and Image Understanding. 110, 3, 346–359. (2008).

DOI: 10.1016/j.cviu.2007.09.014

[2] Z.L. Song: The Research on Image Registration and its Application. Doctorial Dissertation. Shanghai. Fudan University. (2010).

[3] Y.S. Zhu, C.M., Guo: The Relevant Matching Algorithm based on Related Coefficient. Signal Processing, 19(6), 531-534. (2003).

[4] C. Harris, A. Rosenfeld: Gray level corner detector. Pattern Recognition Letters, 1, 95-102 (1982).

[5] T. Lindeberg, M. Bart T. H. Romeny: Linear scale space. (Netherlands: Kluwer Academic Publishers 1994).