Object recognition from local scale-invariant features
Citations
291 citations
290 citations
Cites methods from "Object recognition from local scale..."
...He then creates a Scale Invariant Feature Transform (SIFT) descriptor to match key points using a Euclidean distance metric in an efficient best-bin first algorithm where a match is rejected if the ratio of the best and second best matches is greater than a threshold....
[...]
...The SIFT (Scale Invariant Feature Transform) [9,10] has been shown to perform better than other local descriptors [13]....
[...]
...This paper presents a feature descriptor that combines a local SIFT descriptor [9] with a global context vector similar to shape contexts [2]....
[...]
289 citations
Cites methods from "Object recognition from local scale..."
...This allowed for a more rigorous comparison at the representation-level (model C2b units vs. computer vision features such as SIFT [Lowe, 1999], component-experts [Heisele et al., 2001; Fergus et al., 2003; Fei-Fei et al., 2004], or fragments [Ullman et al., 2002; Torralba et al., 2004]) rather…...
[...]
288 citations
288 citations
Cites background from "Object recognition from local scale..."
...Object recognition is a very well-studied topic in computer vision, and there has been significant progress in many aspects of the problem, from the design of features that are invariant to translation, scaling, and rotation [24], to models for the problem [31], as well as links to other fields [12]....
[...]
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....
[...]