Distinctive Image Features from Scale-Invariant Keypoints
Citations
202 citations
202 citations
Cites methods from "Distinctive Image Features from Sca..."
...It was found to be superior to the established SIFT [12] or SURF [2] descriptors, both in recognition performance and runtime behaviour....
[...]
202 citations
Cites methods from "Distinctive Image Features from Sca..."
...In order to detect key points in EEG signals, we have adopted a technique employed in scale invariant feature transformation [22], which has been a very successful approach for image matching....
[...]
202 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...To extract local features, we can exploit a wealth of interest operators designed to detect a sparse set of salient regions (e.g., Lowe 2004; Mikolajczyk and Schmid 2004; Kadir and Brady 2003), or simply sample densely at regular intervals and at multiple scales....
[...]
...We use PCA to reduce the dimensionality of the SIFT descriptors to 10 before adding the position, yielding features having a total of 12 dimensions....
[...]
...For example, F might be the space of SIFT (Lowe 2004) descriptors (d = 128), or image coordinate positions (d = 2), etc.; a set F contains a collection of these descriptors extracted from a single image or object....
[...]
...To describe each region or patch, we can choose from an array of descriptors designed to capture local texture while maintaining some invariance to small shifts and rotations, such as SIFT (Lowe 2004), shape context (Belongie et al. 2001), or geometric blur (Berg and Malik 2001)....
[...]
...For example, F might be the space of SIFT (Lowe 2004) descriptors (d = 128), or image coordinate positions (d = 2), etc....
[...]
202 citations
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations