Recognition by symmetry derivatives and the generalized structure tensor

@article{Bign2004RecognitionBS,
  title={Recognition by symmetry derivatives and the generalized structure tensor},
  author={Josef Big{\"u}n and Tomas Bigun and Kenneth Nilsson},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2004},
  volume={26},
  pages={1590-1605}
}
We suggest a set of complex differential operators that can be used to produce and filter dense orientation (tensor) fields for feature extraction, matching, and pattern recognition. We present results on the invariance properties of these operators, that we call symmetry derivatives. These show that, in contrast to ordinary derivatives, all orders of symmetry derivatives of Gaussians yield a remarkable invariance: they are obtained by replacing the original differential polynomial with the… CONTINUE READING
Highly Influential
This paper has highly influenced 10 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 157 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 70 extracted citations

Encyclopedia of Biometrics

Springer US • 2015
View 6 Excerpts
Highly Influenced

Eye detection by complex filtering for periocular recognition

2nd International Workshop on Biometrics and Forensics • 2014
View 5 Excerpts
Highly Influenced

SAFE features for matching fingermarks by neighbourhoods of single minutiae

2014 14th International Symposium on Communications and Information Technologies (ISCIT) • 2014
View 5 Excerpts
Highly Influenced

A validated software application to measure fiber organization in soft tissue.

Biomechanics and modeling in mechanobiology • 2016
View 2 Excerpts
Method Support
Highly Influenced

Small infrared target detection based on the complex filter bank

2015 8th International Congress on Image and Signal Processing (CISP) • 2015
View 3 Excerpts
Highly Influenced

Periocular Recognition by Detection of Local Symmetry Patterns

2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems • 2014
View 3 Excerpts
Highly Influenced

158 Citations

01020'02'05'09'13'17
Citations per Year
Semantic Scholar estimates that this publication has 158 citations based on the available data.

See our FAQ for additional information.

References

Publications referenced by this paper.
Showing 1-10 of 37 references