Comparing and evaluating interest points
- 4 January 1998
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 230-235
- https://doi.org/10.1109/iccv.1998.710723
Abstract
Many computer vision tasks rely on feature extraction. Interest points are such features. This paper shows that interest points are geometrically stable under different transformations and have high information content (distinctiveness). These two properties make interest points very successful in the contest of image matching. To measure these two properties quantitatively, we introduce two evaluation criteria: repeatability rate and information content. The quality of the interest points depends on the detector used. In this paper several detectors are compared according to the criteria specified above. We determine which detector gives the best results and show that it satisfies the criteria well.Keywords
This publication has 6 references indexed in Scilit:
- Accuracy in image measurePublished by SPIE-Intl Soc Optical Eng ,1994
- Higher order differential structure of imagesImage and Vision Computing, 1994
- Simulation of neural contour mechanisms: from simple to end-stopped cellsVision Research, 1992
- Finding geometric and relational structures in an imagePublished by Springer Nature ,1990
- A Combined Corner and Edge DetectorPublished by British Machine Vision Association and Society for Pattern Recognition ,1988
- Representation of local geometry in the visual systemBiological Cybernetics, 1987