Distinctive Image Features from Scale-Invariant Keypoints
Citations
93 citations
93 citations
Cites methods from "Distinctive Image Features from Sca..."
...Point feature detectors and descriptors—such as SIFT [17], BRISK [22], etc....
[...]
...A comparison between two images is done through the following pipeline: (i) SIFT [17] image features are extracted in both images; (ii) their descriptors are matched; (iii) outliers are rejected through verification of their geometric consistency via fundamental-matrix estimation (e....
[...]
93 citations
Cites methods from "Distinctive Image Features from Sca..."
...The registration process of the classic SIFT method contains five steps: scale-space extrema detection, keypoint localization, orientation assignment, keypoint descriptor, and keypoint matching [10]....
[...]
...In order to improve the stability of keypoints, Lowe [25] used the Taylor expansion of the scale-space function, D(x, y, σ ) D(x) = D + ∂ D T ∂x x + 1 2 xT ∂2 D ∂x2 x (3) x = (x, y, σ )T is the offset....
[...]
...Lowe recommends that the descriptors are computed by using gradient information of eight directions in a 4 × 4 window within the keypoint scale space....
[...]
...SIFT was first introduced by Lowe [25] in 1999 and then improved in 2004 [10]....
[...]
...Scale-invariant feature transform (SIFT) [10] is one of the most commonly used methods among point feature-based methods, and various improved SIFT-based methods are also widely used....
[...]
92 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...the output of filter banks), color statistics (histogram or moments) and SIFT (Lowe 2004)....
[...]
...The SIFT and color maps are then simply averaged for each category....
[...]
...We make use of two types of low-level descriptors: 128-dimensional SIFT features (Lowe 2004) and 96-dimensional color descriptors....
[...]
...The most popular descriptors include texture (i.e. the output of filter banks), color statistics (histogram or moments) and SIFT (Lowe 2004)....
[...]
...We thus obtain one pixel-level probability map per class per feature type, i.e. one for SIFT and one for color in our case....
[...]
92 citations
Cites methods from "Distinctive Image Features from Sca..."
...It adopts SIFT [18] features and descriptors to match keypoints and uses single value decomposition to estimate position, scale and orientation of the matches....
[...]
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations