Object recognition from local scale-invariant features
Citations
12,449Â citations
Cites methods from "Object recognition from local scale..."
...The DoG detector was kindly provided by David Lowe....
[...]
...Lowe [24] subtracts these pyramid layers in order to get the DoG (Difference of Gaussians) images where edges and blobs can be found....
[...]
...The latter, introduced by Lowe [24], have been shown to outperform the others [28]....
[...]
...Methods include the best-binfirst proposed by Lowe [24], balltrees [35], vocabulary trees [34], locality sensitive hashing [9], or redundant bit vectors [13]....
[...]
...Focusing on speed, Lowe [23] proposed to approximate the Laplacian of Gaussians (LoG) by a Difference of Gaussians (DoG) filter....
[...]
11,201Â citations
Cites methods from "Object recognition from local scale..."
...Ngiam et al. (2011) have used Hybrid Monte Carlo (Neal, 1993), but other options include contrastive divergence (Hinton, 1999; Hinton et al....
[...]
10,501Â citations
8,059Â citations
Additional excerpts
...7 Pyramid match kernels In computer vision, it is common to create a bag-of-words representation of an image by computing a feature vector (often using SIFT (Lowe 1999)) from a variety of points in the image, commonly chosen by an interest point detector....
[...]
7,057Â citations
Cites background or methods from "Object recognition from local scale..."
...Laplacian-of-Gaussians. This detector is similar to DoG approach [ 26 ], which localizes points...
[...]
...SIFT [ 26 ], complex lters [37], moment invariants [43], and cross-correlation for different types of...
[...]
References
[...]
5,672Â citations
4,310Â citations
2,037Â citations
1,756Â 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....
[...]
1,574Â 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....
[...]