Sparse texture representation using affine-invariant neighborhoods Export

@misc{Lazebnik:2003:SpinImages, abstract = {This paper proposes a novel texture representation suitable for recognizing images of textured surfaces under a wide range of transformations, including viewpoint changes and non-rigid deformations. Unlike many existing feature extraction methods, which treat the neighborhood of every pixel as a candidate texture element, the proposed algorithm works by selecting a sparse set of affine-invariant local patches. This spatial selection process, besides providing greater computational efficiency...}, author = {Lazebnik, S. and Schmid, C. and Ponce, J.}, citeulike-article-id = {1378949}, citeulike-linkout-0 = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.5116}, keywords = {descriptor, invariant, rift, rotation, spin-image, thesis}, posted-at = {2007-10-01 02:04:52}, priority = {0}, title = {Sparse texture representation using affine-invariant neighborhoods}, url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.5116}, year = {2003} }

TY - GEN ID - Lazebnik:2003:SpinImages L3 - citeulike-article-id:1378949 N2 - This paper proposes a novel texture representation suitable for recognizing images of textured surfaces under a wide range of transformations, including viewpoint changes and non-rigid deformations. Unlike many existing feature extraction methods, which treat the neighborhood of every pixel as a candidate texture element, the proposed algorithm works by selecting a sparse set of affine-invariant local patches. This spatial selection process, besides providing greater computational efficiency... TI - Sparse texture representation using affine-invariant neighborhoods KW - descriptor KW - invariant KW - rift KW - rotation KW - spin-image KW - thesis AU - Lazebnik, S AU - Schmid, C AU - Ponce, J PY - 2003/// UR - http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.11.5116 ER -