A fully affine invariant image comparison method, Affine-SIFT (ASIFT) is introduced. While SIFT is fully invariant with respect to only four parameters namely zoom, rotation and translation, the new method treats the two left over parameters : the angles defining the camera axis orientation. Against any prognosis, simulating all views depending on these two parameters is feasible. The method permits to reliably identify features that have undergone very large affine distortions measured by a new parameter, the transition tilt. State-of-the-art methods hardly exceed transition tilts of 2 (SIFT), 2.5 (Harris-Affine and Hessian-Affine) and 10 (MSER). ASIFT can handle transition tilts up 36 and higher.

References in zbMATH (referenced in 20 articles , 1 standard article )

Showing results 1 to 20 of 20.
Sorted by year (citations)

  1. Alvarez, Luis; Cuenca, Carmelo; Esclarín, Julio; Mazorra, Luis; Morel, Jean-Michel: Affine invariant distance using multiscale analysis (2016)
  2. Becker, Florian; Petra, Stefania; Schnörr, Christoph: Optical flow (2015)
  3. Farhan, Erez; Hagege, Rami: Geometric expansion for local feature analysis and matching (2015)
  4. Fedorov, Vadim; Arias, Pablo; Sadek, Rida; Facciolo, Gabriele; Ballester, Coloma: Linear multiscale analysis of similarities between images on Riemannian manifolds: practical formula and affine covariant metrics (2015)
  5. El Mir, Ghina; Saint-Jean, Christophe; Berthier, Michel: Conformal geometry for viewpoint change representation (2014)
  6. Mishkin, Dmytro; Matas, Jiří: Matching of images of non-planar objects with view synthesis (2014)
  7. Raviv, Dan; Bronstein, Alexander M.; Bronstein, Michael M.; Waisman, Dan; Sochen, Nir; Kimmel, Ron: Equi-affine invariant geometry for shape analysis (2014)
  8. Tepper, Mariano; Musé, Pablo; Almansa, Andrés: On the role of contrast and regularity in perceptual boundary saliency (2014)
  9. Albarelli, Andrea; Rodolà, Emanuele; Torsello, Andrea: Imposing semi-local geometric constraints for accurate correspondences selection in structure from motion: a game-theoretic perspective (2012)
  10. Delbracio, Mauricio; Almansa, Andrés; Morel, Jean-Michel; Musé, Pablo: Subpixel point spread function estimation from two photographs at different distances (2012)
  11. Sadek, R.; Constantinopoulos, C.; Meinhardt, E.; Ballester, C.; Caselles, V.: On affine invariant descriptors related to SIFT (2012)
  12. Zhang, Zhengdong; Ganesh, Arvind; Liang, Xiao; Ma, Yi: TILT: transform invariant low-rank textures (2012)
  13. Blanchet, G.; Buades, A.; Coll, B.; Morel, J.M.; Rouge, B.: Fattening free block matching (2011)
  14. Morel, Jean-Michel; Yu, Guoshen: Is SIFT scale invariant? (2011)
  15. Paradowski, Mariusz; Śluzek, Andrzej: Local keypoints and global affine geometry: triangles and ellipses for image fragment matching (2011)
  16. Taylor, Simon; Drummond, Tom: Binary histogrammed intensity patches for efficient and robust matching (2011)
  17. Wang, Ning; Yang, Jie: Color image segmentation by edge linking and region grouping (2011)
  18. Chung, Chi-Han; Cheng, Shyi-Chyi; Chang, Chin-Chun: Adaptive image segmentation for region-based object retrieval using generalized Hough transform (2010)
  19. Morel, Jean-Michel; Yu, Guoshen: ASIFT: A new framework for fully affine invariant image comparison (2009)
  20. Rabin, J.; Delon, J.; Gousseau, Y.: A statistical approach to the matching of local features (2009)