Object recognition from local scale-invariant features
Citations
218 citations
Cites background from "Object recognition from local scale..."
...Local invariant features based on gray-level patches have proven very successful for matching and recognition of textured objects [14, 15, 20]....
[...]
218 citations
Additional excerpts
...Thewidebaselineapplicationis describedin section3....
[...]
218 citations
Cites methods from "Object recognition from local scale..."
...In the current exemplar framework slightly worse results on the naming task were obtained by using SIFT (compared to the simple pixel-based descriptor), but this might reasonably be attributed to the SIFT descriptor incorporatingoo muchinvariance to slight appearance changes relevant for discriminating faces....
[...]
...It is natural to consider the use of more established image representations commonly used in face recognition, for example socalled Eigenfaces [26] or Fisherfaces [27], or alternative local feature representations such as SIFT [28] which have successfully been used in feature-matching tasks including face matching [4], especially considering the simplicity of the descriptor proposed here....
[...]
...For example, replacing the pixel-based descriptor with a SIFT [28] descriptor or using Eigen facial-features would give some robustness to image deformation....
[...]
...It is natural to consider the use of more established image repres ntations commonly used in face recognition, for example so-called Eigenfaces [26] or Fisherfaces [27], or alternative local feature representations such as SIFT [28] which have successfully been used in feature-matching tasks including face matching [4], especially considering the simplicity of the descriptor proposed here....
[...]
218 citations
217 citations
Additional excerpts
...The SIFT feature descriptor can overcome affine transformations, changes in the illumination, and changes in the 3-D viewpoint and has thus been widely applied in image analysis [14], [44], [51]....
[...]
References
[...]
5,672 citations
4,310 citations
2,037 citations
1,756 citations
"Object recognition from local scale..." refers background or methods in this paper
...This allows for the use of more distinctive image descriptors than the rotation-invariant ones used by Schmid and Mohr, and the descriptor is further modified to improve its stability to changes in affine projection and illumination....
[...]
...For the object recognition problem, Schmid & Mohr [19] also used the Harris corner detector to identify interest points, and then created a local image descriptor at each interest point from an orientation-invariant vector of derivative-of-Gaussian image measurements....
[...]
..., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
...However, recent research on the use of dense local features (e.g., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
1,574 citations
"Object recognition from local scale..." refers methods in this paper
...[23] used the Harris corner detector to identify feature locations for epipolar alignment of images taken from differing viewpoints....
[...]