Advertisement

Learning

  • Eckart MichaelsenEmail author
  • Jochen Meidow
Chapter
Part of the Advances in Computer Vision and Pattern Recognition book series (ACVPR)

Abstract

The recognition performance, or the degree of consistency of the presented Gestalt operations with human perception, can be improved by introducing some parameters. To this end ground truth is needed on a set of representative images; i.e., Gestalten must be marked on each image that should be found. Not only the data should be representative, but also the set of observers, who do the labeling work. And they need to be instructed properly. Given such labeled data the parameter setting can be improved by supervised machine learning. Examples of parameters are weights corresponding to the different laws in the fusion, a preferred distance for the proximity law, tolerance parameters, etc. In the operations defined in the previous chapters continuous assessment functions are used. Most of these functions are differentiable. Here this property is utilized in order to perform gradient descent optimization on the parameter setting, i.e., learning with each labeled example a little bit. Other possibilities include collecting statistics over features or feature deviations of found positive and negative example Gestalten. Then the parameter setting is similar to estimating parametrized distributions based on empirical statistics.

References

  1. 1.
    Liu J, Slota G, Zheng G, Wu Z, Park M, Lee S, Rauschert I, Liu Y (2013) Symmetry detection from realworld images competition 2013: summary and results. In: CVPR 2013, workshopsGoogle Scholar
  2. 2.
    Funk C, Lee S, Oswald MR, Tsokas S, Shen W, Cohen A, Dickinson S, Liu Y (2017) 2017 ICCV challenge: detecting symmetry in the wild. In: ICCV 2017, workshopsGoogle Scholar
  3. 3.
    Kanizsa G (1980) Grammatica del vedere. Saggi su percezione e gestalt. Il MulinoGoogle Scholar
  4. 4.
    Grenander U (1993) General pattern theory. Oxford University PressGoogle Scholar
  5. 5.
    Mumford D, Desolneux A (2010) Pattern theory. CRC Press, A K Peters Ltd., Natick MAzbMATHGoogle Scholar
  6. 6.
    Fisher NI (1995) Statistical analysis of circular data. Cambridge University PressGoogle Scholar
  7. 7.
    Michaelsen E, Arens M (2017) Hierarchical grouping using gestalt assessments. In: CVPR 2017, workshops, detecting symmetry in the wildGoogle Scholar
  8. 8.
    Michaelsen E, Meidow J (2014) Stochastic reasoning for structural pattern recognition: an example from image-based uav navigation. Pattern Recognit 47(8):2732–2744CrossRefGoogle Scholar
  9. 9.
    Pohl M, Meidow J, Bulatov D (2017) Simplification of polygonal chains by enforcing few distinctive edge directions. In: Sharma P, Bianchi FM (eds) Scandinavian conference on image analysis (SCIA). Lecture Notes in Computer Science, Part II, vol 10270, pp 1–12CrossRefGoogle Scholar
  10. 10.
    Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J R Stat Soc Ser B 39(1):1–38MathSciNetzbMATHGoogle Scholar
  11. 11.
    Akaike H (1973) Information theory and an extension of the maximum likelihood principle. Springer, New York, pp 199–213Google Scholar
  12. 12.
    Schwarz G (1978) Estimating the dimension of a model. Ann Stat 6:461–464MathSciNetCrossRefGoogle Scholar
  13. 13.
    Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Susstrunk S (2012) SLIC superpixels compared to state-of-the-art superpixel, methods. Trans Pattern Anal and Mach Intell 34(11):2274–2281CrossRefGoogle Scholar
  14. 14.
    Michaelsen E, Yashina VV (2014) Simple gestalt algebra. Pattern Recognit Image Anal 24(4):542–551CrossRefGoogle Scholar
  15. 15.
    Desolneux A, Moisan L, Morel J-M (2008) From gestalt theory to image analysis: a probabilistic approach. SpringerGoogle Scholar
  16. 16.
    Michaelsen E, Münch D, Arens M (2016) Searching remotely sensed images for meaningful nested gestalten. In: ISPRS 2016Google Scholar
  17. 17.
    Sarkar S, Boyer KL (1994) Computing perceptual organization in computer vision. World ScientificGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Fraunhofer IOSBEttlingenGermany

Personalised recommendations