Symmetrical patterns in natural images

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Пронин С.В. Симметричные паттерны в изображениях природных сцен // Оптический журнал. 2022. Т. 89. № 1. С. 24–32. http://doi.org/10.17586/1023-5086-2022-89-01-24-32

Pronin S.V. Symmetrical patterns in natural images [in Russian] // Opticheskii Zhurnal. 2022. V. 89. № 1. P. 24–32. http://doi.org/10.17586/1023-5086-2022-89-01-24-32

For citation (Journal of Optical Technology):

S. V. Pronin, "Symmetrical patterns in natural images," Journal of Optical Technology. 89(1), 17-22 (2022). https://doi.org/10.1364/JOT.89.000017

Abstract:

One of the approaches to image analysis is based on the use of visual alphabets comprising the compact patterns characteristic of the images of a particular class. Elements of these alphabets can be either obtained from a theoretical model describing the basic image structures or extracted directly from the training sets. Symmetric patterns characteristic of the images of outdoor scenes were investigated in this study. The choice of this pattern class is driven by the fact that the objects of interest usually have at least local symmetry. Furthermore, selection of only symmetric patterns allows most fragments of random textures that in most cases do not have symmetry to be dismissed. The image set used in this study comprised 829 monochromatic photographs showing natural objects and textures at different scales. Fragments with diameters of 13 pixels having 1 of 9 symmetry types were selected from this set. The obtained sets of symmetric fragments were processed using a density-based spatial clustering of applications with noise (DBSCAN) cluster analysis algorithm, which allows clusters of arbitrary shape to be analyzed. Fifteen pattern types were obtained; five of them have not previously been used as elements of visual alphabets. Most of the obtained patterns have reflection symmetry, which agrees with the results of psychophysical studies, according to which reflection symmetry is identified faster than other symmetry types. The obtained data can be used for the formation of elements of visual alphabets as well as for synthesizing the stimuli for the experiments in the field of vision physiology.

Keywords:

image structure, visual alphabets, images of outdoor scenes, symmetrical patterns, DBSCAN

OCIS codes: 100.2960, 330.5000

References:

1. Ramanan A., Niranjan M. A review of codebook models in patch-based visual object recognition // J. Signal Processing Systems. 2012. V. 68. P. 333–352
2. Lillholm M., Griffin L. Novel image feature alphabets for object recognition // 19th Internat. Conf. Pattern Recognition. Tampa, USA. 2008, Dec. 8–11. V. 1. P. 1–4.
3. Aslan S., Akgül C., Sankur B., Tunali T. SymPaD: Symbolic patch descriptor // Proc. 10th Internat. Conf. Computer Vision Theory and Applications. Berlin, Germany. 2015, March 11–14. V. 2. P. 266–271.
4. Lee A.B., Pedersen K.S., Mumford D. The nonlinear statistics of high-contrast patches in natural images // Internat. J. Computer Vision. 2003. V. 54. P. 83–103.
5. Agarwal S., Roth D. Learning a sparse representation for object detection // Proc. Seventh European Conf. Computer Vision. Copenhagen, Denmark. 2002, May 28–31. V. 4. P. 113–130.
6. Leibe B., Schiele B. Interleaved object categorization and segmentation // Proc. British Machine Conf. / Ed. Harvey R., Bangham A. Durham: BMVA Press, 2003. P. 78.1–78.10.
7. Harris C., Stephens M. A combined corner and edge detector // Proc. Fourth Alvey Vision Conf. Manchester, UK. 1988, Aug. 31 — Sept. 2. P. 147–151.
8. Jurie F., Triggs B. Creating efficient codebooks for visual recognition // 10th IEEE Internat. Conf. on Computer Vision. Beijing, China. 2005, Oct. 17–21. V. 1. P. 604–610.
9. Wagemans J. Detection of visual symmetries // Spatial Vision. 1995. V. 9. № 1. P. 9–32.
10. Griffin L. Symmetries of 2-D images: Cases without periodic translations // J. Mathematical Imaging and Vision. 2009. V. 34. № 3. P. 259–269.
11. Keys R. Cubic convolution interpolation for digital image processing // IEEE Trans. Acoustics, Speech, and Signal Proc. 1981. V. 29. № 6. P. 1153–1160.
12. Ester M., Kriege H.P., Sander J., Xu X. A density-based algorithm for discovering clusters in large spatial databases with noise // Proc. Second Internat. Conf. Knowledge Discovery and Data Mining. Portland, Oregon. 1996. P. 226–231
13. van Hateren J.H., Ruderman D.L. Independent component analysis of natural image sequences yields spatiotemporal filters similar to simple cells in primary visual cortex // Proc. Royal Soc. of London. 1998. V. 265. P. 2315–2320.
14. Royer E. Detection of symmetry // J. Experimental Psychology: Human Perception and Performance. 1981. V. 7. № 6. P. 1186–1210.
15. Tyler С. Human symmetry perception and its computational analysis. London: Lawrence Erlbaum Associates, Inc., 2002. 393 p.