Distinctive Image Features from Scale-Invariant Keypoints
Citations
261 citations
Cites background from "Distinctive Image Features from Sca..."
...The most popular and successful local descriptors are orientation histograms including SIFT [19] and HOG [5], which are robust to minor transformations of images....
[...]
...Kernel descriptors include SIFT and HOG as special cases, and provide a principled way generate rich patch-level features from various pixel attributes....
[...]
...Experiments on both CIFAR10 and the RGB-D Object Dataset (available at http://www.cs.washington.edu/rgbd-dataset) show that hierarchical kernel descriptors outperform kernel descriptors and many state-of-the-art algorithms including deep belief nets, convolutional neural networks, and local coordinate coding with carefully tuned SIFT features....
[...]
...The combination of three hierarchical kernel descriptors has an accuracy of 80.0%, higher than all other competing techniques; its accuracy is 14.4 percent higher than SIFT, 9.0 percent higher than mcRBM combined with DBNs, and 5.5 percent higher than the improved LCC. Hierarchical kernel descriptors slightly outperform the very recent work: the convolutional RBM and the triangle Kmeans with 4000 centers [4]....
[...]
...Hua et al. [10] learned a linear transformation for SIFT using linear discriminant analysis and showed better results with lower dimensionality than SIFT on local feature matching problems....
[...]
261 citations
Cites background from "Distinctive Image Features from Sca..."
...Thirdly, a key point orientation assignment based on local image gradient and lastly a descriptor generator to compute the local image descriptor for each key point based on image gradient magnitude and orientation [3]....
[...]
...Although SIFT has proven to be very efficient in object recognition applications, it requires a large computational complexity which is a major drawback especially for real-time applications [3, 4]....
[...]
...Scale Invariant Feature Transform (SIFT) is a feature detector developed by Lowe in 2004 [3]....
[...]
258 citations
257 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...Tables VIII and IX illustrate the fusion results from both the RGB and depth using PCA, LBP, and LGBP (SIFT is not used because it cannot capture the correct information from depth images as shown in Section IV-D2)....
[...]
...Because the depth map is highly smooth, the SIFT-based method is inappropriate for 2.5-...
[...]
...PCA [19] (i.e., the Eigenface method), LBP [21], SIFT [81], and LGBP [34]-based methods are selected as the baseline techniques for the 2-...
[...]
...SIFT-based method extracts the key points from all training and testing images, where the similarity measure is achieved by key points matching....
[...]
...In the contrary, since LBP, SIFT, and LGBP are local-based methods, they are more robust to such local distortions....
[...]
255 citations
Cites background or methods from "Distinctive Image Features from Sca..."
...In our research, regarding [21], the feature contrast (i....
[...]
...Therefore, extrema in which the ratio of H eigenvalues is above a threshold, for example, Tr = 10 (proposed in [21]), are considered as points corresponding to edges and discarded (for more explanations, see [21])....
[...]
...03 (a threshold proposed by Lowe [21])....
[...]
...SIFT features are scale invariant and accurate, and they are robust against illumination differences, changes in 3-D viewpoint, and image noise [21]....
[...]
...The famous SIFT algorithm proposed by Lowe [21] consists of three main modules: feature extraction, feature description,...
[...]
References
46,906 citations
16,989 citations
13,993 citations
7,057 citations
3,422 citations