Abstract
This work presents scale invariant region detectors that apply evolved operators to extract an interest measure. We evaluate operators using their repeatability rate, and have experimentally identified a plateau of local optima within a space of possible interest operators Ω. The space Ω contains operators constructed with Gaussian derivatives and standard arithmetic operations. From this set of local extrema, we have chosen two operators, obtained by searching within Ω using Genetic Programming, that are optimized for high repeatability and global separability when imaging conditions are modified by a known transformation. Then, by embedding the operators into the linear scale space generated with a Gaussian kernel we can characterize scale invariant features by detecting extrema within the scale space response of each operator. Our scale invariant region detectors exhibit a high performance when compared with state-of-the-art techniques on standard tests.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 27(10), 1615–1630 (2005)
Schmid, C., Mohr, R., Bauckhage, C.: Evaluation of interest point detectors. Int. J. Comput. Vision 37(2), 151–172 (2000)
Trujillo, L., Olague, G.: Synthesis of interest point detectors through genetic programming. In: Proceedings of GECCO 2006, vol. 1, pp. 887–894. ACM Press, New York, NY, USA (2006)
Trujillo, L., Olague, G.: Using Evolution to Learn How to Perform Interest Point Detection. In: Proceedings of ICPR 2006, vol. 1, pp. 211–214. IEEE Comput. Soc. Washington, DC, USA (2006)
Mikolajczyk, K., Schmid, C.: Scale and Affine Invariant Interest Point Detectors. Int. J. Comput. Vision 60(1), 63–86 (2004)
Lindeberg, T.: Discrete Scale-Space Theory and the Scale-Space Primal Sketch. PhD thesis, Computational Vision and Active Perception Laboratory (CVAP) Royal Institute of Technology, Sweden (1991)
Harris, C., Stephens, M.: A combined corner and edge detector, in Alvey Vision Conference, pp. 147–151 (1988)
Förstner, W.: A framework for low level feature extraction, In: Proceedings of the 3rd European Conference on Computer Vision, pp. 383–394 (1994)
Beaudet, P.R.: Rotational invariant image operators, In: Proceedings of the 4th International Joint Conference on Pattern Recognition, pp. 579–583 (1978)
Wang, H., Brady, J.M.: Corner detection for 3d vision using array processors. In: Proceedings from BARNAIMAGE-91, Springer-Verlag, Berlin Heidelberg, New York (1991)
Ebner, M., Zell, A.: Evolving Task Specific Image Operator. In: Poli, R., Voigt, H.-M., Cagnoni, S., Corne, D.W., Smith, G.D., Fogarty, T.C. (eds.) Proceedings from EvoIASP’99 and EuroEcTel’99. LNCS, vol. 1596, pp. 74–89. Springer-Verlag, Berlin Heidelberg New York (1999)
Young, R.A.: Simulation of the Human Retinal Function with the Gaussian Derivative Model, In: Proceedings of the 1986 IEEE Conference on Computer Vision and Pattern Recognition, pp. 564–569 (1986)
Lindeberg, T.: Feature detection with automatic scale selection. Int. J. Comput. Vision 30(2), 79–116 (1998)
Visual Geometry Group: http://www.robots.ox.ac.uk/ vgg/research/
Lowe, D.G.: Object recognition from local scale-invariant features. Proceedings of CVPR 1999, IEEE Comput. Soc. 2, 1150–1157 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Trujillo, L., Olague, G. (2007). Scale Invariance for Evolved Interest Operators. In: Giacobini, M. (eds) Applications of Evolutionary Computing. EvoWorkshops 2007. Lecture Notes in Computer Science, vol 4448. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-71805-5_47
Download citation
DOI: https://doi.org/10.1007/978-3-540-71805-5_47
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-71804-8
Online ISBN: 978-3-540-71805-5
eBook Packages: Computer ScienceComputer Science (R0)