Object recognition from local scale-invariant features
Citations
146Â citations
Cites background or methods from "Object recognition from local scale..."
...By quantizing the continuous-valued local features, e.g. SIFT descriptors [16], over a collection of representative visual atoms, called codebook or dictionary, BoW simply represents an image or object as a codebook-based histogram which is then fed into standard classifiers (e.g. SVM) for classification....
[...]
...Given an image, the spatial pyramid feature [14] is computed as the representation by max pooling the sparse codes of the SIFT descriptors in a three-level spatial pyramid configuration which is then used as feature in SVMs for classification in ScSPM, IMDL and JDL. Note that the classification scheme presented in Section 3.4 is also used in IMDL as multiple dictionaries are trained....
[...]
...Specifically, we adopt a dense sampling strategy to select the interest regions from which SIFT descriptors are extracted....
[...]
...The SIFT [16] descriptor is used as local descriptor due to its excellent performance on object recognition [3, 25, 13]....
[...]
...SIFT descriptors [16], over a collection of representative visual atoms, called codebook or dictionary, BoW simply represents an image or object as a codebook-based histogram which is then fed into standard classifiers (e....
[...]
146Â citations
Cites background from "Object recognition from local scale..."
...One line of research is the extension towards multi-camera systems and to include for instance depth sensors....
[...]
145Â citations
145Â citations
Cites background or methods from "Object recognition from local scale..."
...advanced detector such as the one described in [8] could be used instead....
[...]
...The keypoint descriptor in [8] handles this problem by carefully assuring that a gradient vector contributes to the same local histogram even in case of small positional shifts....
[...]
...Scale-invariant feature extraction can be achieved by using the Harris detector [13] at several Gaussian derivative scales, or by considering local optima of pyramidal difference-of-Gaussian filters in scale-space [8]....
[...]
145Â citations
References
[...]
5,672Â citations
4,310Â citations
2,037Â citations
1,756Â citations
"Object recognition from local scale..." refers background or methods in this paper
...This allows for the use of more distinctive image descriptors than the rotation-invariant ones used by Schmid and Mohr, and the descriptor is further modified to improve its stability to changes in affine projection and illumination....
[...]
...For the object recognition problem, Schmid & Mohr [19] also used the Harris corner detector to identify interest points, and then created a local image descriptor at each interest point from an orientation-invariant vector of derivative-of-Gaussian image measurements....
[...]
..., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
...However, recent research on the use of dense local features (e.g., Schmid & Mohr [19]) has shown that efficient recognition can often be achieved by using local image descriptors sampled at a large number of repeatable locations....
[...]
1,574Â citations
"Object recognition from local scale..." refers methods in this paper
...[23] used the Harris corner detector to identify feature locations for epipolar alignment of images taken from differing viewpoints....
[...]