29 January 2014 Local sharpness distribution–based feature points matching algorithm
Author Affiliations +
An efficient descriptor and a complete scheme for removing incorrect correspondences are two essentials for accurate feature points matching in image processing and pattern recognition. This paper proposes a new rigid feature points matching algorithm. First, a new feature descriptor based on the local sharpness distribution is proposed to extract features, which leads to a feature set of extremely low dimensionality. With these features, the normalized cross-correlation coefficient and a bidirectional matching strategy are employed to generate the initial feature point correspondences. Then a complete scheme with two rules is proposed to remove the probable incorrect correspondences. Owing to these two rules based on the voting strategy and the ratio of the distances, respectively, the accuracy of feature points matching is remarkably improved. Experimental results show that the proposed algorithm is efficient for feature matching and comparisons with other algorithms show its better comprehensive performance.
© 2014 SPIE and IS&T
Yue Zhao, Yue Zhao, Jianbo Su, Jianbo Su, } "Local sharpness distribution–based feature points matching algorithm," Journal of Electronic Imaging 23(1), 013011 (29 January 2014). https://doi.org/10.1117/1.JEI.23.1.013011 . Submission:


An approach to image clustering and retrieval
Proceedings of SPIE (April 29 2018)
Edge Detection In Cytology Using Morphological Filters
Proceedings of SPIE (April 04 1989)
A robust stamp detection framework on degraded documents
Proceedings of SPIE (January 15 2006)
Stereo matching based on phase congruency corner detector
Proceedings of SPIE (October 23 2006)
Computer-assisted extraction of boundaries from images
Proceedings of SPIE (April 13 1993)

Back to Top