Distinctive Image Features from Scale-Invariant Keypoints
Citations
429 citations
Cites methods from "Distinctive Image Features from Sca..."
...The feature extraction is performed in two steps: detecting regions of interest with the Hessian-Affine detector [14], and computing SIFT descriptors for these regions [11]....
[...]
...BOF image search systems [20] first extract a set of local descriptors for each image, such as the popular SIFT descriptor [11]....
[...]
...Note that the descriptor is similar in spirit to the local SIFT descriptor [11]....
[...]
...The BOF framework [20] is based on local invariant descriptors [14, 11] extracted at invariant regions of interest....
[...]
423 citations
Cites methods from "Distinctive Image Features from Sca..."
...For the SIFT feature, we densely sampled and computed the SIFT descriptors of 16 × 16 patches over a grid with spacing of 8 pixels....
[...]
...For details on these feature descriptors, we refer the readers t o [1, 3, 12, 24]....
[...]
...We have experimented with several feature sets for face analysis in recent work: Local Binary Patterns (LBP) [1], LEarning-based (LE) [3], SIFT [12], and Three-Patch LBP (TPLBP) [24]....
[...]
421 citations
Cites methods from "Distinctive Image Features from Sca..."
...Researchers have developed a wide spectrum of different local descriptors [17, 16, 5, 22], bag-of-words models [14, 24] and classification methods [4], and they compared to the best available results on those publicly available datasets – for PASCAL VOC, many teams from all over the world participate in the PASCAL Challenge each year to compete for the best performance....
[...]
419 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...SIFT features, proposed by Lowe [2], are features (keypoints) extracted from images to help in reliable matching between different views of the same object, image classification, and object recognition....
[...]
...Keypoints are detected by robust feature detection methods like SIFT [2], its variant principal component analysis (PCA)-SIFT [14] and...
[...]
...In [2], SIFT was used for extracting distinctive invariant features from images that can be invariant to image scale and rotation....
[...]
...In Lowe’s original implementation [2] a 4-by-4 patch of histograms with 8 bins each is used, generating a 128-dimensional feature vector....
[...]
417 citations
Cites methods from "Distinctive Image Features from Sca..."
...By combining OSS and TSS using both LDA and SVM, over variants of LBP and SIFT descriptors, this method has set the current state-of-the-art results on LFW. Nguyen and Bai [20] apply cosine similarity metric learning (CSML) to face verification, combining pixel intensity, LBP, and Gabor representations....
[...]
...The majority of existing methods for face verification rely on feature representations given by hand-crafted image descriptors, such as SIFT [18] and Local Binary Patterns (LBP) [22]....
[...]
...Wolf et al. [38] combine hand-crafted image descriptors such as LBP, Gabor, and SIFT, and additionally combine each of these representations for six different similarity metrics....
[...]
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations