Distinctive Image Features from Scale-Invariant Keypoints
Citations
88 citations
Cites methods from "Distinctive Image Features from Sca..."
...the SIFT [14], as well as various combinations of these....
[...]
...Techniques Used for Visual Classification The Xerox team, which obtained the best results, uses a Fisher Vector representation of the images built on low level features such as Scale Invariant Feature Transform (SIFT), Local Orientation Histograms (ORH) and local RGB statistics [11]....
[...]
...Tools such as the GIFT4 (GNU Image Finding Tool) [12] were employed as well as techniques such as the Color Layout Descriptor (CLD) of MPEG–7, the Color and Edge Directivity Descriptor (CEDD), the Fuzzy Color and Texture Histogram (FCTH) using the Lucene image retrieval (LIRE) library5 [13], 4 http://www.gnu.org/software/gift/ 5 http://freshmeat.net/projects/lirecbir/ the SIFT [14], as well as various combinations of these....
[...]
88 citations
Cites background from "Distinctive Image Features from Sca..."
...1) Weighting Local Features in the Transformed Space: Given a local descriptor set for representing the collections of all the local features extracted from each frame within a video, where denotes the th local feature (Scale-Invariant Feature Transform (SIFT) descriptor [17] in this paper), denotes the dimension of the feature descriptor, denotes the number of all the local features extracted from the given video....
[...]
...In recent years, local visual features, such as the scale-invariant feature transform (SIFT) descriptor [17], have been playing a more significant role in many applications of video content analysis due to their distinctive representation capacity [15], [22], [35], [36]....
[...]
88 citations
Cites methods from "Distinctive Image Features from Sca..."
...Scale invariant feature transform (SIFT) [20] and speeded up robust features (SURF) have also been used to extract texture features [21], [22]....
[...]
88 citations
Cites background from "Distinctive Image Features from Sca..."
...[3], which first constructs a sparse descriptor database by extracting SIFT features [4] at training time....
[...]
88 citations
Cites methods from "Distinctive Image Features from Sca..."
...The adopted matching strategy begins with finding a small number of robust correspondences between the two images using a ‘winner takes all’ strategy and the SIFT descriptor [38]....
[...]
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations