Distinctive Image Features from Scale-Invariant Keypoints
Citations
112 citations
Cites background from "Distinctive Image Features from Sca..."
...To test the effect of Super-Bit depth N , we fix K = 120 for Photo Tourism SIFT and K = 3000 for MIR-Flickr respectively, and to test the effect of code length K, we fix N = 120 for Photo Tourism SIFT and N = 3000 for MIR-Flickr....
[...]
..., bag-of-words representation of documents and images, and histogram-based representations like SIFT local descriptor [20]....
[...]
...We conduct the experiment on the following datasets: 1) Photo Tourism patch dataset1 [26], Notre Dame, which contains 104,106 patches, each of which is represented by a 128D SIFT descriptor (Photo Tourism SIFT); and 2) MIR-Flickr2, which contains 25,000 images, each of which is represented by a 3125D bag-of-SIFT-feature histogram; For each dataset, we further conduct a simple preprocessing step as in [12], i.e. mean-centering each data sample, so as to obtain additional mean-centered versions of the above datasets, Photo Tourism SIFT (mean), and MIR-Flickr (mean)....
[...]
..., the normalized bag-of-words representation for documents, images, and videos, and the normalized histogram-based local features like SIFT [20]....
[...]
...In real applications, many vector representations are limited in non-negative orthant with all vector entries being non-negative, e.g., bag-of-words representation of documents and images, and histogram-based representations like SIFT local descriptor [20]....
[...]
112 citations
Cites methods from "Distinctive Image Features from Sca..."
...Traditionally, approaches relied on point descriptors such as SIFT [15] for place recognition....
[...]
111 citations
Cites methods from "Distinctive Image Features from Sca..."
...In our implementation, the low-level features are SIFT descriptors (Lowe 2004) whose dimensionality is reduced from 128 down to 32 dimensions....
[...]
111 citations
Cites background from "Distinctive Image Features from Sca..."
...Please refer to [38] for further details on SIFT extraction....
[...]
...SIFT descriptors [38] characterize image regions invariant to image scale, rotation, and 3D camera viewpoint....
[...]
...5, similar to the criterion proposed in [38]....
[...]
111 citations
Cites background from "Distinctive Image Features from Sca..."
...SIFT features capture the distribution of edge orientation energy in each patch [20]....
[...]
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations