Corner Localization in Digital Images Based on Radon Transform

Authors

Xuguang Wang, North China Electric Power University, Hebei Engineering Research Center of Simulation &Optimized Control for Power Generation, Baoding 071003, China;
Zhang Qin, North China Electric Power University, Hebei Engineering Research Center of Simulation &Optimized Control for Power Generation, Baoding 071003, China;
Su Jie, North China Electric Power University, Hebei Engineering Research Center of Simulation &Optimized Control for Power Generation, Baoding 071003, China;

Abstract

Abstract: Location accuracy is one of the key indexes of measuring the performance of feature point.. High location accuracy feature point detection has important implications for the applications such as 3D reconstruction, motion estimation, target tracking and recognition, image registration, etc. A corner location algorithm based on Radon transform is proposed.Edge binary images are obtained with traditional method first, ideal straight lines and curves are extracted then, potential corner locations are calculated next, fake corners are rejected finally. Experimental results on both simulation and real images show that, this method performs better than the existing methods on interest point localization accuracy. Meanwhile, the strategy makes this method robust to image noises.

Recommended Citation

Wang, Xuguang; Qin, Zhang; and Jie, Su (2019) "Corner Localization in Digital Images Based on Radon Transform," Journal of System Simulation: Vol. 31: Iss. 10, Article 23.
DOI: 10.16182/j.issn1004731x.joss.17-0420
Available at: https://dc-china-simulation.researchcommons.org/journal/vol31/iss10/23

First Page

2164

Revised Date

2017-11-07

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.17-0420

Last Page

2173

CLC

TN911.73

Recommended Citation

Wang Xuguang, Zhang Qin, Su Jie. Corner Localization in Digital Images Based on Radon Transform[J]. Journal of System Simulation, 2019, 31(10): 2164-2173.

DOI

10.16182/j.issn1004731x.joss.17-0420