Fast Keypoint Recognition in Ten Lines of Code

By Mustafa Özuysal, Pascal Fua, Vincent Lepetit. 2007

529 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Deep Structured Output Learning for Unconstrained Text Recognition (2014, background): “The character classiﬁers include random ferns (Ozuysal et al. (2007)) in Wang et al. (2011), and CNNs in Wang et al. (2012); Jaderberg et al. (2014c).”
Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition (2014, methodology): “The sliding window classifiers include random ferns [22] in Wang et al.”
Reading Text in the Wild with Convolutional Neural Networks (2014, methodology): “(2011) use a random ferns (Ozuysal et al. 2007) classifier trained onHOG features (Felzenszwalb et al.”
PROST: Parallel robust online simple tracking (2010, methodology): “Many different tracking methods have been proposed, from global template-based trackers [2], shape-based methods, probabilistic models using mean-shift [7] or particle filtering [13] to local key-point based trackers [14] or flow-based trackers [19].”
Random Forests and Decision Trees (2012, unknown): “[9, 10].”
Accurate Non-Iterative O(n) Solution to the PnP Problem (2007, methodology): “We tested our algorithm on noisy correspondences, that may include erroneous ones, obtained on real images with our implementation of the keypoint recognition method of [18].”
BRIEF: Computing a Local Binary Descriptor Very Fast (2012, background): “In other words, unlike earlier systems, such as our own real-time mouse pad detection application presented in [42], this one does not require a training phase, which may take several minutes.”
Approximate Nearest Neighbor Search by Residual Vector Quantization (2010, methodology): “The method that transforming tree-like structure to flat structure, which has been used in ferns classifier [25], significant reduces the complexity of index structure while maintaining a fine-grained division of space.”
Pose tracking from natural features on mobile phones (2008, methodology): “Contrary to descriptor-based matching as described in the last section, feature classification for tracking [18] works by learning the distribution of some features F of a set of classes C corresponding to model points mC in a model image.”
P-N learning: Bootstrapping binary classifiers by structural constraints (2010, background): “Our classifier consists of a number a ferns [18] (simplified trees) that are evaluated in parallel on each patch.”
Multiple 3D Object tracking for augmented reality (2008, methodology): “The state-of-the-art is probably the tracking-by-detection approach of [8], which is the starting point of our method.”
Text-Attentional Convolutional Neural Network for Scene Text Detection (2015, methodology): “explored Random Ferns classifier [18] with a histogram of oriented gradients (HOG) feature [19] for text detection.”
Fast Keypoint Recognition Using Random Ferns (2010, methodology): “The code that implements patch evaluation can be written in 10 lines of C++ code, which highlights the simplicity of the resulting implementation and the complete software package is available [29].”
Image Classification using Random Forests and Ferns (2007, result): “This is in contrast to random ferns where if few ferns are used the variance is very large, however as the number of ferns is increased the random selection method does not cause large variations on the classifier performance [21].”
Visual Tracking: an Experimental Survey (2013, unknown): “The authors use the fast Random Ferns [70] to learn the detector.”
The power of comparative reasoning (2011, background): “Several papers talk about using pairwise pixel comparisons or related quantities for pattern matching [7, 13, 14, 15, 16, 17].”
Deep Features for Text Spotting (2014, methodology): “For example, Wang et al. [45] use a random ferns [38] sliding window classiﬁer to ﬁnd characters in an image, grouping them using a pictorial structures model [18] for a ﬁxed lexicon.”