Abstract

We propose to use binary strings as an efficient feature point descriptor, which we call BRIEF. We show that it is highly discriminative even when using relatively few bits and can be computed using simple intensity difference tests. Furthermore, the descriptor similarity can be evaluated using the Hamming distance, which is very efficient to compute, instead of the L-2 norm as is usually done.

Keywords

Hamming distanceComputer scienceDiscriminative modelBinary numberPattern recognition (psychology)Similarity (geometry)Hamming weightArtificial intelligenceHamming codePoint (geometry)Feature (linguistics)AlgorithmBinary codeNorm (philosophy)MathematicsArithmeticBlock codeDecoding methodsImage (mathematics)

Affiliated Institutions

Related Publications

Low-density parity-check codes

Robert G. Gallager

A low-density parity-check code is a code specified by a parity-check matrix with the following properties: each column contains a small fixed number <tex xmlns:mml="http://www....

1962 IEEE Transactions on Information Theory 10397 citations

Channel coding with multilevel/phase signals

G. Ungerboeck

A coding technique is described which improves error performance of synchronous data links without sacrificing data rate or requiring more bandwidth. This is achieved by channel...

1982 IEEE Transactions on Information Theory 3729 citations

Publication Info

Year
2010
Type
book-chapter
Pages
778-792
Citations
3503
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

3503
OpenAlex

Cite This

Michael Calonder, Vincent Lepetit, Christoph Strecha et al. (2010). BRIEF: Binary Robust Independent Elementary Features. Lecture notes in computer science , 778-792. https://doi.org/10.1007/978-3-642-15561-1_56

Identifiers

DOI
10.1007/978-3-642-15561-1_56