Distinctive Image Features from Scale-Invariant Keypoints
Citations
158 citations
158 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...The kd-tree (Freidman et al. 1977) is one such approach that has often been employed to match local descriptors, in several variants (e.g., (Lowe 2004, Beis & Lowe 1997, Muja & Lowe 2009, Silpa-Anan & Hartley 2008))....
[...]
...Due to the specificity of state-of-the-art feature descriptors such as SIFT (Lowe 2004) or SURF (Bay et al....
[...]
...The most popular choice for this step is the SIFT descriptor (Lowe 2004), which we present in detail in the following....
[...]
...An often-used strategy (initially proposed by Lowe (2004)) is to consider the ratio of the distance to the closest neighbor to that of the second-closest one as a decision criterion....
[...]
...Local features (such as SIFT (Lowe 2004)) are independently extracted from both images, and their descriptors are matched to establish putative correspondences....
[...]
158 citations
157 citations
Cites methods from "Distinctive Image Features from Sca..."
...Recently, scale-invariant feature transform (SIFT) [5] has been widely applied to many matching applications....
[...]
157 citations
Cites methods from "Distinctive Image Features from Sca..."
...We have experimented with using the gray values themselves, color histograms, SIFT [15], and SIFT+gray descriptors....
[...]
...As Figure 5 shows, it seems that SIFT+gray values is the most suitable for our problem....
[...]
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations