Advertisement

Neural Computing and Applications

, Volume 31, Supplement 2, pp 1155–1163 | Cite as

Towards semantic segmentation of orthophoto images using graph-based community identification

  • Abdelmalik MoujahidEmail author
  • Fadi Dornaika
  • Yassine Ruichek
  • Karim Hammoudi
Original Article
  • 103 Downloads

Abstract

We present an unsupervised framework that automatically detects objects of interest in images by formulating the general problem of semantic segmentation as community detection problem in graphs. The framework broadly follows a four-step procedure. First, we perform an over-segmentation of the original image using the well-known statistical region merging algorithm which presents the advantage of not requiring any quantization or colour space transformations. Second, we compute the feature descriptors of the resulting segmented regions. For encoding colour and other textural information, each region is described by an hybrid descriptor based on colour histograms and covariance matrix descriptor. Third, from the set of descriptors we construct different weighted graphs using various graph construction algorithms. Finally, the resulting graphs are then divided into groups or communities using a community detection algorithm based on spectral modularity maximization. This algorithm makes use of the eigenspectrum of matrices such as the graph Laplacian matrix and the modularity matrix which are more likely to reveal the community structure of the graph. Experiments conducted on large orthophotos depicting several zones in the region of Belfort city situated on the north-eastern of France provide promising results. The proposed framework can be used by semi-automatic approaches to handle the challenging problems of scene parsing.

Keywords

Semantic segmentation Aerial images Feature descriptors Graph construction methods Spectral clustering Community detection 

Notes

Compliance with ethical standards

Conflict of interest

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

References

  1. 1.
    Farabet C, Couprie C, Najman L, LeCun Y (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915–1929CrossRefGoogle Scholar
  2. 2.
    Socher R, Lin CC, Ng AY, Manning CD (2011) Parsing natural scenes and natural language with recursive neural networks. In: International conference on machine learningGoogle Scholar
  3. 3.
    Sharma P, Suji J (2016) A review on image segmentation with its clustering techniques. Int J Signal Process Image Process Pattern Recognit 9(5):209–218Google Scholar
  4. 4.
    Newman MEJ (2006) Modularity and community structure in networks. Proc Natl Acad Sci 103(23):8577–8582CrossRefGoogle Scholar
  5. 5.
    Sousa C, Rezende S, Batista G (2013) Influence of graph construction on semi-supervised learning. In: European conference on machine learning, pp 160–175Google Scholar
  6. 6.
    Zhang L, Chen S, Qiao L (2012) Graph optimization for dimensionality reduction with sparsity constraints. Pattern Recognit 45:1205–1210CrossRefzbMATHGoogle Scholar
  7. 7.
    Zhang L, Qiao L, Chen S (2010) Graph-optimized locality preserving projections. Pattern Recognit 43:1993–2002CrossRefzbMATHGoogle Scholar
  8. 8.
    Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15(6):1373–1396CrossRefzbMATHGoogle Scholar
  9. 9.
    Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326CrossRefGoogle Scholar
  10. 10.
    Schaeffer SE (2007) Graph clustering. Comput Sci Rev 1(1):2007CrossRefGoogle Scholar
  11. 11.
    Fortunato S (2010) Community detection in graphs. Phys Rep 486(3–5):75–174MathSciNetCrossRefGoogle Scholar
  12. 12.
    Bandyopadhyay S, Chowdhary G, Sengupta D (2015) Focs: fast overlapped community search. IEEE Trans Knowl Data Eng 27(11):2974–2985CrossRefGoogle Scholar
  13. 13.
    Xu D, Tian Y (2015) A comprehensive survey of clustering algorithms. Ann Data Sci 2(2):165–193MathSciNetCrossRefGoogle Scholar
  14. 14.
    Hu H (2015) Graph based models for unsupervised high dimensional data clustering and network analysis. Ph.D. thesis, University of CaliforniaGoogle Scholar
  15. 15.
    Sajana T, Rani CMS, Narayana KV (2016) A survey on clustering techniques for big data mining. Indian J Sci Technol 9(3):1–12CrossRefGoogle Scholar
  16. 16.
    Garima, Gulati H, Singh PK (2015) Clustering techniques in data mining: a comparison. In: 2015 2nd international conference on computing for sustainable global development (INDIACom), pp 410–415Google Scholar
  17. 17.
    Kernighan BW, Lin S (1970) An efficient heuristic procedure for partitioning graphs. Bell Syst Tech J 49(2):291–307CrossRefzbMATHGoogle Scholar
  18. 18.
    Guo C, Zheng S, Xie Y, Hao W (2012) A survey on spectral clustering. In: World Automation Congress 2012, Puerto Vallarta, Mexico, pp 53–56Google Scholar
  19. 19.
    Yang P, Zhu Q, Huang B (2011) Spectral clustering with density sensitive similarity function. Knowl Based Syst 24:621–628CrossRefGoogle Scholar
  20. 20.
    Wacquet G, Caillault EP, Hamad D, Hebert PA (2013) Constrained spectral embedding for k-way data clustering. Pattern Recognit Lett 34(9):1009–1017CrossRefGoogle Scholar
  21. 21.
    Wang X, Qian B, Davidson I (2014) On constrained spectral clustering and its applications. Data Min Knowl Discov 28(1):1–30MathSciNetCrossRefzbMATHGoogle Scholar
  22. 22.
    Newman MEJ (2006) Finding community structure in networks using the eigenvectors of matrices. Phys Rev E 74:036104MathSciNetCrossRefGoogle Scholar
  23. 23.
    Nock R, Nielsen F (2004) Statistical region merging. IEEE Trans Pattern Anal Mach 26(11):1452–1458CrossRefGoogle Scholar
  24. 24.
    Dornaika F, Moujahid A, Merabet YE, Ruichek Y (2016) Building detection from orthophotos using a machine learning approach: an empirical study on image segmentation and descriptors. Expert Syst Appl 58:130–142CrossRefGoogle Scholar
  25. 25.
    Tuzel O, Porikli F, Meer P (2006) A fast descriptor for detection and classification. In: European conference on computer vision, pp 589–600Google Scholar
  26. 26.
    Ojala T, Pietikainen M, Maenpaa T (2002) Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Trans Pattern Anal Mach Intell 24:971–987CrossRefzbMATHGoogle Scholar
  27. 27.
    Takala V, Ahonen T, Pietikainen M (2005) Block-based methods for image retrieval using local binary patterns. In: Image analysis, SCIA, vol LNCS, p 3540Google Scholar
  28. 28.
    Ahonen T, Hadid A, Pietikainen M (2006) Face description with local binary patterns: application to face recognition. IEEE Trans Pattern Anal Mach Intell 28(12):2037–2041CrossRefzbMATHGoogle Scholar
  29. 29.
    Bereta M, Karczmarek P, Pedrycz W, Reformat M (2013) Local descriptors in application to the aging problem in face recognition. Pattern Recognit 46:2634–2646CrossRefGoogle Scholar
  30. 30.
    Huang D, Shan C, Ardabilian M, Wang Y (2011) Adaptive particle sampling and adaptive appearance for multiple video object tracking. IEEE Trans Syst Man Cybern Part C Appl Rev 41(6):765–781CrossRefGoogle Scholar
  31. 31.
    Wolf L, Hassner T, Taigman Y (2008) Descriptor based methods in the wild. In: Faces in real-life images workshop in ECCVGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  1. 1.Signal Theory and Communications Department (DTSC)Carlos III University of Madrid (UC3M)GetafeSpain
  2. 2.University of the Basque Country (UPV/EHU) and Ikerbasque FoundationSan SebastianSpain
  3. 3.University of Technology of Belfort-Montbeliard (UTBM)SevenansFrance
  4. 4.University Haute Alsace, UHAMulhouseFrance

Personalised recommendations