Distinctive Image Features from Scale-Invariant Keypoints
Citations
156 citations
Cites methods from "Distinctive Image Features from Sca..."
...The success of R-CNN method [5] is largely attributed to the ability of CNN model to extract more richer high-level object representation features as opposed to handengineered low-level features such as SIFT [31] and HOG [32]....
[...]
156 citations
156 citations
Cites background from "Distinctive Image Features from Sca..."
...The rise of effective descriptors for point features that exhibit a degree of viewpoint invariance (e.g. Lowe 2004 or Lepetit et al. 2005) has seen realtime methods for point-based model-based tracking become more effective, such as Wagner et al. (2008) or Ozuysal et al. (2006) (where the model is…...
[...]
156 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...If descriptor A in a sketch is assigned to B in the image, then B must also be nearest to A for a valid match [16]....
[...]
...4 we evaluate SSIM, alongside SIFT and HoG descriptors for the purpose of sketch based shape retrieval and show our adapted GF-HOG descriptor outperforms these on both our own Flickr160 dataset1 and the ETHZ extended object dataset (a subset of which is used in [11])....
[...]
...We compare retrieval performance with an otherwise identical system incorporating alternative descriptors: the Self-Similarity (SSIM) [10, 11], SIFT [16], and HoG [14] descriptor....
[...]
...Here, SIFT is computed on a region of radius 16 pixels....
[...]
...This simple technique yields significant improvements in performance when matching sketches to photos, compared to three leading descriptors: Self-Similarity Descriptor (SSIM); SIFT; and HoG (sec....
[...]
156 citations
Cites methods from "Distinctive Image Features from Sca..."
...The original 128-dimensional SIFT descriptors were introduced by Lowe.2 In our experiment, we accomplish the extraction using the software implementation of Van de Sande, Gevers, and Snoek.3 We use a bag-ofwords model with a vocabulary of 500 words and perform the clustering process using the k-means algorithm....
[...]
...The original 128-dimensional SIFT descriptors were introduced by Lowe.(2) In our experiment, we accomplish the extraction using the software implementation of Van de Sande, Gevers, and Snoek....
[...]
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations