Title :
Image matching for repetitive patterns
Author :
Lu Tian ; Xianwei Xu ; Jie Zhou
Author_Institution :
Dept. of Autom., Tsinghua Univ., Beijing, China
Abstract :
Repetitive patterns exist widely in real world images, and matching images with plenty of repetitive patterns remains a challenging task. We present in this paper a novel feature matching algorithm of images with notably repetitive patterns, in which a reliable initial correspondence set is established, purified and propagated using a voting strategy, incorporating a local geometrical constraint. Experiments have demonstrated that the proposed algorithm outperforms state-of-the-art feature matching methods on matching images with plenty of repetitive patterns.
Keywords :
feature extraction; image matching; feature matching algorithm; image matching; local geometrical constraint; real world images; repetitive pattern matching; voting strategy; Buildings; Computer vision; Feature extraction; Image registration; Pattern matching; Robustness; Feature correspondence; repetitive pattern;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on
Conference_Location :
South Brisbane, QLD
DOI :
10.1109/ICASSP.2015.7178218
