Jump to content

Scale-invariant feature operator

From Wikipedia, the free encyclopedia

In the fields of computer vision and image analysis, the scale-invariant feature operator (or SFOP) is an algorithm to detect local features in images. The algorithm was published by Förstner et al. in 2009.[1]

Algorithm

[edit]

The scale-invariant feature operator (SFOP) is based on two theoretical concepts:

  • spiral model[2]
  • feature operator[3]

Desired properties of keypoint detectors:

  • Invariance and repeatability for object recognition
  • Accuracy to support camera calibration
  • Interpretability: Especially corners and circles, should be part of the detected keypoints (see figure).
  • As few control parameters as possible with clear semantics
  • Complementarity to known detectors

scale-invariant corner/circle detector.

Theory

[edit]

Maximize the weight

[edit]

Maximize the weight = 1/variance of a point

  

comprising:

1. the image model[2]

2. the smaller eigenvalue of the structure tensor

Reduce the search space

[edit]

Reduce the 5-dimensional search space by

  • linking the differentiation scale to the integration scale
  • solving for the optimal using the model
  • and determining the parameters from three angles, e. g.
  • pre-selection possible:

Filter potential keypoints

[edit]
  • non-maxima suppression over scale, space and angle
  • thresholding the isotropy :
    eigenvalues characterize the shape of the keypoint, smallest eigenvalue has to be larger than threshold
    derived from noise variance and significance level :

Algorithm

[edit]
Algorithm
Algorithm

Results

[edit]

Interpretability of SFOP keypoints

[edit]

See also

[edit]

References

[edit]
  1. ^ Forstner, Wolfgang; Dickscheid, Timo; Schindler, Falko (2009). "Detecting interpretable and accurate scale-invariant keypoints". 2009 IEEE 12th International Conference on Computer Vision. pp. 2256–2263. CiteSeerX 10.1.1.667.2530. doi:10.1109/ICCV.2009.5459458. ISBN 978-1-4244-4420-5.
  2. ^ a b Bigün, J. (1990). "A Structure Feature for Some Image Processing Applications Based on Spiral Functions". Computer Vision, Graphics, and Image Processing. 51 (2): 166–194.
  3. ^ Förstner, Wolfgang (1994). "A Framework for Low Level Feature Extraktion". European Conference on Computer Vision. Vol. 3. Stockholm, Sweden. pp. 383–394.
[edit]