(45-4) 11 * << * >> * Russian * English * Content * All Issues

Extended set of superpixel features
A.A. Egorova 1, V.V. Sergeyev 1,2

Samara National Research University, 443086, Samara, Russia, Moskovskoye Shosse 34,
IPSI RAS – Branch of the FSRC "Crystallography and Photonics" RAS,
443001, Samara, Russia, Molodogvardeyskaya 151

 PDF, 1441 kB

DOI: 10.18287/2412-6179-CO-876

Pages: 562-574.

Full text of article: Russian language.

Superpixel-based image processing and analysis methods usually use a small set of superpixel features. Expanding the description of superpixels can improve the quality of processing algorithms. In the paper, a set of 25 basic superpixel features of shape, intensity, geometry, and location is proposed. The features meet the requirements of low computational complexity in the process of image superpixel segmentation and sufficiency for solving a wide class of application tasks. Applying the set, we present a modification of the well-known approach to the superpixel generation. It consists of fast primary superpixel segmentation of the image with a strict homogeneity predicate, which provides superpixels preserving the intensity information of the original image with high accuracy, and the subsequent enlargement of the superpixels with softer homogeneity predicates. The experiments show that the approach can significantly reduce the number of image elements, which helps to reduce the complexity of processing algorithms, meanwhile the expanded superpixels more accurately correspond to the image objects.

superpixel segmentation, feature, invariant moments, polynomial approximation.

Egorova AA, Sergeyev VV. Extended set of superpixel features. Computer Optics 2021; 45(4): 562-574. DOI: 10.18287/2412-6179-CO-876.

This work was supported by the Russian Foundation for Basic Research under project No. 19-37-90116 and the Russian Federation Ministry of Science and Higher Education within a state contract with the "Crystallography and Photonics" Research Center of the RAS under agreement 007-ГЗ/Ч3363/26.


  1. Yaroslavskiy LP. Introduction to digital imaging [In Russian]. Moscow: "Sovetskoe Radio" Publisher; 1979.
  2. Pratt WK. Digital image processing. 4th ed. Hoboken, NJ: John Wiley & Sons Inc; 2007.
  3. Vittikh VA, Sergeev VV, Soifer VA. Image processing in automated systems for scientific research [In Russian]. Moscow: "Nauka" Publisher; 1982.
  4. Pavlidis T. Algorithms for graphics and image processing. Berlin: Springer Science & Business Media; 2012.
  5. Soifer VA, ed. Computer image processing, Part II: Methods and algorithms. Saarbrücken: VDM Verlag Dr Müller; 2010. ISBN: 978-3-639-17545-5.
  6. Gonzalez RC, Woods RE. Digital image processing. London: Pearson; 2018.
  7. Achanta R, et al. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 2012; 34(11): 2274-2282.
  8. Stutz D, Hermans A, Leibe B. Superpixels: An evaluation of the state-of-the-art. Comput Vis Image Underst 2018; 166: 1-27.
  9. Felzenszwalb PF, Huttenlocher DP. Efficient graph-based image segmentation. Int J Comput Vis 2004; 59(2): 167-181.
  10. Vedaldi A, Soatto S. Quick shift and kernel methods for mode seeking. Proc European Conference on Computer Vision 2008: 705-718.
  11. Levinshtein A, Stere A, Kutulakos K, Fleet D, Dickinson S, Siddiqi K. Turbopixels: Fast superpixels using geometric flows. IEEE Trans Pattern Anal Mach Intell 2009; 31(12): 2290-2297.
  12. Veksler O, Boykov Y, Mehrani P. Superpixels and supervoxels in an energy optimization framework. In Book: Daniilidis K, Maragos P, Paragios N, eds. Berlin, Heidelberg: Springer-Verlag; 2010: 211-224.
  13. Blokhinov YB, Gorbachev VA, Rakutin YO, Nikitin AD. A real-time semantic segmentation algorithm for aerial imagery. Computer Optics 2018; 42(1): 141-148. DOI: 10.18287/2412-6179-2018-42-1-141-148.
  14. Liu M, et al. Entropy rate superpixel segmentation. Proc IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2011: 2097-2104.
  15. Wang J, Wang X. VCells: Simple and efficient superpixels using edge-weighted centroidal Voronoi tessellations. IEEE Trans Pattern Anal Mach Intell 2012; 34(6): 1241-1247.
  16. Conrad C, Mertz M, Mester R. Contour-relaxed superpixels. In Book: Heyden A, Kahl F, Olsson C, Oskarsson M, Tai X-C, eds. Energy minimization methods in computer vision and pattern recognition. Heidelberg: Springer; 2013: 280-293.
  17. Shen J, Du Y, Wang W, Li X. Lazy random walks for superpixel segmentation. IEEE Trans Image Process 2014; 23(4): 1451-1462.
  18. Neubert P, Protzel P. Compact watershed and preemptive SLIC: On improving trade-offs of superpixel segmentation algorithms. 2014 22nd Int Conf on Pattern Recognition 2014; 996-1001.
  19. Van den Bergh M, et al. SEEDS: Superpixels extracted via energy-driven sampling. Int J Comput Vis 2015; 111(3): 298-314.
  20. Li Z, Chen J. Superpixel segmentation using linear spectral clustering. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015: 1356-1363.
  21. Wei X, et al. Superpixel hierarchy. IEEE Trans Image Process 2018; 27(10): 4838-4849.
  22. Fu K, Mui J. A survey on image segmentation. Pattern Recogn 1981; 13(1): 3-16.
  23. Denisov DA, Nizovkin VA. Segmentation of images on computers [In Russian]. Zarubegnaya Radioelektronika 1985; 10: 5-31.
  24. Haralick R, Shapiro L. Image segmentation techniques. Comput Vis Graph Image Process 1985; 29(2): 100-132.
  25. Pal N, Pal S. A review on image segmentation techniques. Pattern Recogn 1993; 26(9): 1277-1294.
  26. Mehnert A, Jackway O. An improved seeded region growing algorithm. Pattern Recogn Lett 1997; 18(10): 1065-1071.
  27. Chukin YuV. Data structures for representing images [In Russian]. Zarubegnaya Radioelektronika 1983; 8: 35-47.
  28. Wang M, et al. Superpixel segmentation: A benchmark. Signal Process Image Commun 2017; 56: 28-39.
  29. Neubert P, Protzel P. Superpixel benchmark and comparison. Forum Bildverarbeitung 2012: 1-12.
  30. Schick A, Fischer M, Stiefelhagen R. An evaluation of the compactness of superpixels. Pattern Recogn Lett 2014; 43: 71-80.
  31. Schick A, Fischer M, Stiefelhagen R. Measuring and evaluating the compactness of superpixels. Proc International Conference on Pattern Recognition 2012: 930-934.
  32. Sergeev VV, Soifer VA. Imitation model of images and a data compression method. Automatic Control and Computer Sciences 1978; 12(3): 75-77.
  33. Sergeev VV. Method of video data compression using the criterion of uniform approximation [In Russian]. Questions of Cybernetics. Coding and Transmission of Information in Computer Networks 1978; (42): 146-149.
  34. Csillik O. Fast segmentation and classification of very high resolution remote sensing data using SLIC superpixels. Remote Sensing 2017; 9(3): 1-19.
  35. Li S, et al. Multi-scale superpixel spectral-spatial classification of hyperspectral images. Int J Remote Sens 2016; 37(20): 4905-4922.
  36. Liauchuk VA, Kovalev VA. A method for quantitative description of biomedical images based on superpixel dictionaries [In Russian]. Informatics 2016; (1): 49-57.
  37. Lucks L, et al. Superpixel-wise assessment of building damage from aerial images. Proc 14th Int Joint Conf on Computer Vision, Imaging and Computer Graphics Theory and Applications 2019; 4: 211-220.
  38. Gould S, et al. Multi-class segmentation with relative location prior. Int J Comput Vis 2008; 80: 300-316.
  39. Barnard K, et al. Matching words and pictures. J Mach Learn Res 2003; 3(2): 1107-1135.
  40. Hoiem D, Efros AA, Hebert M. Geometric context from a single image. 10th IEEE Int Conf on Computer Vision (ICCV'05) 2005; 1: 654-661.
  41. Tighe J, Lazebnik S. SuperParsing: Scalable nonparametric image parsing with superpixels. Int J Comput Vis 2010; 101(2): 352-365.
  42. Malisiewicz T, Efros AA. Recognition by association via learning per-exemplar distances. 2008 IEEE Conference on Computer Vision and Pattern Recognition 2008: 1-8.
  43. Hoiem D, et al. Recovering occlusion boundaries from a single image. 2007 IEEE 11th Int Conf on Computer Vision 2007: 1-8.
  44. Cheng J, Liu J, Xu Y. Superpixel classification for initialization in model based optic disc segmentation. Annual Int Conf IEEE Engineering in Medicine and Biology Society 2012; 1450-1453.
  45. Pont-Tuset J, et al. Multiscale combinatorial grouping for image segmentation and object proposal generation. IEEE Trans Pattern Anal Mach Intell 2016; 39(1): 128-140.
  46. Ilyasova NYu, Ustinov, AV, Khramov, AG. Algorithms for the automated clustering of the microparticles image [In Russian]. Computer Optics 1993; 13: 39-46.
  47. Abramov NS, Khachumov, VM. Object recognition based on invariant moments [In Russian]. Bulletin of the Peoples' Friendship University of Russia Series Mathematics, Computer science, Physics 2014; 2: 142-149.
  48. Anisimov BV, Kurganov VD, Zlobin VK. Recognition and digital image processing [In Russian]. Moscow: "Vysshaya shkola" Publisher; 1983.
  49. Hu MK. Visual pattern recognition by moment invariants. IEEE Trans Inf Theory 1962; 8(2): 179-187.
  50. Maitra S. Moment invariants. Proc IEEE 1979; 67(4): 697-699.
  51. Glumov NI. Construction and application of moment in-variants for image processing in a sliding window [In Russian]. Computer Optics 1995; 14-15(1): 46-54.
  52. Linnik YuV. The method of least squares and the foundations of the mathematical and statistical theory of observation processing [In Russian]. Moscow: "Fizmatlit" Publisher; 1952.
  53. Liu T, Seyedhosseini M, Tasdizen T. Image segmentation using hierarchical merge tree. IEEE Trans Image Process 2016; 25(10): 4596-4607.
  54. Setyanto A, Woods J. Hierarchical visual content modelling and query based on trees. Electron Lett Comput Vis Image Anal 2016; 15(2): 40-42.
  55. Jiao X, Chen Y, Dong R. An unsupervised image segmentation method combining graph clustering and high-level feature representation. Neurocomputing 2020; 409: 83-92.
  56. Galvão FL, et al. Image segmentation using dense and sparse hierarchies of superpixels. Pattern Recogn 2020; 108: 1-14.
  57. Treméau A, Colantoni P. Regions adjacency graph applied to color image segmentation. IEEE Trans Image Process 2000; 9(4): 735-744.
  58. Harary F. Graph theory. Boston: Addison-Wesley; 1971.
  59. Ren Z, Shakhnarovich G. Image Segmentation by cascaded region agglomeration. 2013 IEEE Conf on Computer Vision and Pattern Recognition 2013: 2011-2018.
  60. Wang K, Li L, Zhang J. End-to-end trainable network for superpixel and image segmentation. Pattern Recogn Lett 2020; 140: 135-142.
  61. Chang K. Machine learning based image segmentation. Paris: Université PSL; 2019.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20