27 February 2012 Feature matching using modified projective nonnegative matrix factorization
Author Affiliations +
We present a novel matching method to find the correspondences among different images containing the same object. In the proposed method, by considering each feature point-set as a matrix, two point-sets are projected onto a common subspace using modified projective nonnegative matrix factorization. The core idea of the proposed approach is to jointly factorize of the two feature matrices and the matching operate on embeddings of the two point-sets in the common subspace. Furthermore, it is robust to noise due to the merit of the subspace method. The proposed approach was tested for matching accuracy, and robustness to noise. Its performance on synthetic and real images was compared with state-of-the-art reference algorithms.
© 2012 SPIE and IS&T
Weidong Yan, Weidong Yan, Zheng Tian, Zheng Tian, Jinhuan Wen, Jinhuan Wen, Lulu Pan, Lulu Pan, } "Feature matching using modified projective nonnegative matrix factorization," Journal of Electronic Imaging 21(1), 013005 (27 February 2012). https://doi.org/10.1117/1.JEI.21.1.013005 . Submission:


Wavelet-based image registration
Proceedings of SPIE (April 15 2010)
Global invariant methods for object recognition
Proceedings of SPIE (November 01 2001)
Image matching using algebraic topology
Proceedings of SPIE (January 17 2006)

Back to Top