Advertisement

Search

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

Abstract

Recurring application of Gestalt operations to a set of primitives extracted from an image in an attempt to search for hierarchically organized patterns can cause considerable computational loads. It turns out important to bound the amount of computation and storage requirements so that the practical application of such Gestalt recognition becomes robust and feasible. This chapter gives several possibilities: Stratified enumeration implements a breadth-first search. Pruning is achieved by the use of an assessment threshold.

References

  1. 1.
    Michaelsen E, Münch D, Arens M (2013) Recognition of symmetry structure by use of gestalt algebra. In: CVPR 2013 competition on symmetry detectionGoogle Scholar
  2. 2.
    Michaelsen E (2014a) Searching for rotational symmetries based on the gestalt algebra operation. In: OGRW 2014, 9th Open german-russian workshop on pattern recognition and image understandingGoogle Scholar
  3. 3.
    Michaelsen E (2014b) Gestalt algebra—a proposal for the formalization of gestalt perception and rendering. Symmetry 6(3):566–577MathSciNetCrossRefGoogle Scholar
  4. 4.
    Michaelsen E, Gabler R, Scherer-Negenborn N (2015) Towards understanding urban patterns and structures. In: Photogrammetric image analysis PIA 2015, archives of ISPRSCrossRefGoogle Scholar
  5. 5.
    Michaelsen E, Arens M (2017) Hierarchical grouping using gestalt assessments. In: CVPR 2017, workshops, detecting symmetry in the wildGoogle Scholar
  6. 6.
    Michaelsen E, Münch D, Arens M (2016) Searching remotely sensed images for meaningful nested gestalten. In: ISPRS 2016Google Scholar
  7. 7.
    Michaelsen E, Yashina VV (2014) Simple gestalt algebra. Pattern Recogn Image Anal 24(4):542–551CrossRefGoogle Scholar
  8. 8.
    Wenzel S (2016) High-level facade image interpretation using marked point processes. PhD thesis, Department of Photogrammetry, University of BonnGoogle Scholar
  9. 9.
    Korč F, Förstner W (2009) eTRIMS image database for interpreting images of man-made scenes. Technical Report TR-IGG-P-2009-01, Department of Photogrammetry, University of Bonn. http://www.ipb.uni-bonn.de/projects/etrims_db/. Accessed Aug 2018
  10. 10.
    Tyleček R (2016) Probabilistic models for symmetric object detection in images. PhD thesis, Czech Technical University in PragueGoogle Scholar
  11. 11.
    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
  12. 12.
    Michaelsen E, Doktorski L, Lütjen K (2012) An accumulating interpreter for cognitive vision production systems. Pattern Recogn Image Anal 22(3):1–6CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Fraunhofer IOSBEttlingenGermany

Personalised recommendations