Object recognition from local scale-invariant features
Citations
578 citations
Cites methods from "Object recognition from local scale..."
...In the object recognition domain, patches xi;j in each image are obtained using the SIFT detector [13], each patch xi;j is then represented by a feature vector ðxi;jÞ that incorporates a combination of SIFT descriptor and relative location and scale features....
[...]
574 citations
Cites methods from "Object recognition from local scale..."
...Some methods involve statistical training based on local features, e.g. gradient-based features such as HOG [1], EOH [8], and some involve extracting interest points in the image, such as scale-invariant feature transform (SIFT) [9], etc....
[...]
573 citations
568 citations
Cites background or methods from "Object recognition from local scale..."
...In summary, our system differs from other wide baseline stereo methods in that we do not apply a search between images but process each image and each local feature individually (Gruen, 1985; Super and Klarquist, 1997; Schaffalitzky and Zisserman, 2001), in that we fully take into account the affine deformations caused by the change in viewpoint (Lowe, 1999; Montesinos et al., 2000; Schmid and Mohr, 1997; Dufournaud et al., 2000) and in that we can deal with general 3D objects without assuming specific structures to be present in the image (Pritchett and Zisserman, 1998; Tell and Carlsson, 2000)....
[...]
...For instance, Lowe (1999) uses extrema of a difference of Gaussians filter....
[...]
...The consistency of the matches found is tested using semi-local constraints, followed by a test on the epipolar geometry using RANSAC. As shown in the experimental results, the feasibility of affine invariance even on a local scale has been demonstrated. Robust matching is quite a generic problem in vision and several other applications can be considered. Object recognition is one, where images of an object can be matched against a small set of reference images of the same object. The sample set can be kept small because of the invariance. Moreover, as the features are local, recognition against variable backgrounds and under occlusion is supported by this method. Another application is grouping, where symmetries can be found as repeated structures. Image database retrieval can also benefit from these regions, where other pictures of the same scene or object can be found. Here, the viewpoint and illumination invariance gives the system the capacity to generalize to a great extent from a single query image. Finally, being able to match a current view against learned views can allow robots to roam extended spaces, without the need for a 3D model. Initial results for such applications can be found in Tuytelaars and Van Gool (1999), Tuytelaars et al....
[...]
...…Klarquist, 1997; Schaffalitzky and Zisserman, 2001), in that we fully take into account the affine deformations caused by the change in viewpoint (Lowe, 1999; Montesinos et al., 2000; Schmid and Mohr, 1997; Dufournaud et al., 2000) and in that we can deal with general 3D objects without assuming…...
[...]
...Lowe (1999) has extended these ideas to real scale-invariance, using circular regions that maximize the output of a difference of gaussian filters in scale space, while Hall et al. (1999) not only applied automatic scale selection (based on Lindeberg (1998)), but also retrieved the orientation of…...
[...]
565 citations
Cites methods from "Object recognition from local scale..."
...…(Morel and Yu, 2009), BRIEF (Calonder et al., 2010) and LDAHash (Strecha et al., 2012)), the Scale Invariant Feature Transform (SIFT) object recognition system is used most widely in SfM (Lowe, 1999, 2001, 2004) and has been shown by Lowe (2004) to perform well for changes in viewpoint of <40 ....
[...]
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....
[...]