Distinctive Image Features from Scale-Invariant Keypoints
Citations
76 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...Candidates were chosen based on the Euclidian distance of their descriptor vectors using the nearest neighbour algorithm (Lowe, 2004)....
[...]
...From the images, the SIFT algorithm extracts distinctive invariant feature points that can be used to perform reliable matching between views of an object and scene (Lowe, 1999; Lowe, 2004)....
[...]
...between views of an object and scene (Lowe, 1999; Lowe, 2004)....
[...]
75 citations
Cites methods from "Distinctive Image Features from Sca..."
...The image descriptor is a combination of Hessian-Affine region detector [27] and SIFT descriptor [28]....
[...]
75 citations
Cites background from "Distinctive Image Features from Sca..."
...They found that GLOH [73] and SIFT [66] are the two best performed descriptors among others in their settings....
[...]
..., Harr wavelets features, Gabor features, and those in the spatial domain, especially various gradient-based features, such as Local Binary Patterns (LBP, [2]), Scale Invariant Feature Transform (SIFT [66]) and Gradient Location-Orientation Histogram (GLOH [73])....
[...]
...Popular feature set descriptors include those in frequency domain, e.g., Harr wavelets features, Gabor features, and those in the spatial domain, especially various gradient-based features, such as Local Binary Patterns (LBP, [2]), Scale Invariant Feature Transform (SIFT [66]) and Gradient Location-Orientation Histogram (GLOH [73])....
[...]
75 citations
Cites methods from "Distinctive Image Features from Sca..."
...44 using SIFT [12] in our implementation....
[...]
...When using the same configuration, their approach is worse than ours, as either indicated in [22] as well as implemented by us using their published LibHIK1 code, which is 81.36± 0.54 using CENTRIST [23] and 78.66±0.44 using SIFT [12] in our implementation....
[...]
...For feature extraction, we use dense sampling strategy and SIFT features [12] as our descriptor, which are computed on a 16 × 16 patches over a grid with spacing of 8 pixels for all datasets....
[...]
...In [1], they extracted SIFT features using multi-scale patches densely sampled from each image, which result in much redundant features on the training set (about 15000 to 20000 features per image)....
[...]
75 citations
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations