Author : Kavitha H 1
Date of Publication :11th April 2019
Abstract: Feature matching refers to estimating robust feature correspondences between two images of same scene, which maps the key points from source to target data set. In this work an effective approach is used in the form of Progressive Sparse Spatial Consensus (PSSC) for finding more true matches from a putative set of feature correspondences. The key purpose is performing sparse approximation progressively based on spatial consensus. This significantly reduces the computation complexity as well as covers the more true matches. The spatial transformation between images is characterized by non-parametric thin plate spline kernel which enables our progressive Sparse Spatial Consensus method to handle non-rigid and rigid motions of the image pairs. The Expectation Maximization along with the maximum likelihood model is used to estimate and optimize the degree of true match. The quantitative outcomes obtained on publicly accessible data sets are verified with the results of various algorithms shows that our approach outstands in the rate of precision, recall and f-measure specifically in the case of large-scale outliers
- J. Ma, J. Zhao, J. Jiang, and H. Zhou, “Non-rigid point set registration with robust transformation estimation under manifold regularization,” in Proc. AAAI Conf. Artif. Intel, pp. 4218-4224, 2017.
- M. A. Fischler and R. C. Bolles, “Random sample consensus: A paradigm for model fitting with application to image analysis and automated cartography,” Commun. ACM, vol. 24, no. 6, pp. 381- 395, 1981
- X. Li and Z. Hu, “Rejecting mismatches by correspondence function,” Int. J. Comput. Vis., vol. 89, no. 1, pp. 1-17, 2010.
- J. Chen, J. Ma, C. Yang, and J. Tian, “Mismatch removal via coherent spatial relations,” J. Electron. Imaging, vol. 23, no. 4, p. 043012, 2014.
- J. Ma, J. Zhao, J. Tian, A. L. Yuille, and Z. Tu, “Robust point matching via vector field consensus,” IEEE Trans. Image Process., vol. 23, no. 4, pp. 1706-1721, Apr. 2014.
- J. Ma, H. Zhou, J. Zhao, Y. Gao, J. Jiang, and J. Tian, “Robust feature matching for remote sensing image registration via locally linear transforming,” IEEE Trans. Geosci. Remote Sens., vol. 53, no. 12, pp. 6469- 6481, Dec. 2015.
- G.Wahba, Spline Models for Observational Data. Philadelphi, PA, USA: SIAM, 1990.
- B.D. Lucas and T.Kanade, “An iterative image registration technique with an application to stereo vision,” in Proc. Int. Joint Conf. Artif. Intel. pp. 674- 679, 1981.
- J. Ashburner, “A fast diffeomorphic image registration algorithm,” vol. 38, no. 1, pp. 95-113, 2007
- FujiaJu, Yanfeng Sun, JunbinGao, Siemeng Liu, YongliHu, “Image outlier detection and Feature Extraction via L1-Norm based 2D Probabilistic PCA”, IEEE trans. Image Processing, vol.24 ,no. 12, 2015.