Skip to main content
Log in

The use of contextual spatial knowledge for low-quality image segmentation

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In this paper, a novel possibilistic approach for representing pixelic spatial knowledge is proposed to be used in classification; more specifically in segmentation of low quality images. This approach uses the spatial contextual information at the pixel level in order to produce a local possibility distribution. The similarity between this local possibility distribution representing the contextual pixelic information and the possibility distribution for each of the predetermined thematic classes is measured. This measure is used to assign one of these thematic classes to the pixel. In order to show the potential of the proposed possibilistic approach, synthetic and real images (Melanoma) are classified using the possibilistic similarity. The performance is compared with four relevant classic methods and one recent theory-like method (fuzzy c means). Our context-based possibilistic representation approach outperforms the other methods, in terms of classification recognition rate as well as in stability or robustness behavior when compared to those methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15

Similar content being viewed by others

References

  1. Aarts EH, Van Laarhoven PJ (1985) Statistical cooling: A general approach to combinatorial optimization problems. Philips J Res 40(4):193–226

    MathSciNet  Google Scholar 

  2. Alsahwa B, Almouahed S, Gueriot D, Solaiman B (2013) Iterative possibility distributions refining in pixel-based images classification framework. In: Proceedings of the 2nd internationalconference on pattern recognition applications and methods, pp. 176-181. https://doi.org/10.5220/0004264901760181

  3. Alsahwa B, Solaiman B, Almouahed S, Bossé É, Guériot D (2016) Iterative refinement of possibility distributions by learning for pixel-based classification. IEEE Trans Image Process 25:3533–3545

    Article  MathSciNet  Google Scholar 

  4. Balducci F, Grana C (2017) Pixel classification methods to detect skin lesions on dermoscopic medical images. In: Battiato S, Gallo G, Schettini R, Stanco F (eds) Image analysis and processing - ICIAP 2017. ICIAP 2017. Lecture notes in computer science, vol 10485. Springer, Cham

  5. Bansal A, Chen X, Russell B, Gupta A, Ramanan D (2017) PixelNet: Representation of the pixels, by the pixels, and for the pixels. arXiv:1702.06506 [cs.CV]

  6. Besag JE (1986) On the Statistical Analysis of Dirty Pictures. J R Stat Soc Ser B 48(3):259–302

    MathSciNet  MATH  Google Scholar 

  7. Dhara SRR, Suryono S, Widodo CE (2017) Determination of breast cancer area from mammography images using thresholding method. International Journal of Innovative Research in Advanced Engineering (IJIRAE) ISSN: 2349-2163 4(06):80–83

    Google Scholar 

  8. Diamond S, Sitzmann V, Boyd S, Wetzstein G, Heide F (2017) Dirty Pixels: Optimizing image classification architectures for raw sensor data. ArXiv:cs.CV 1701.06487, ArXiv. Report available from https://arxiv.org/abs/1701.06487

  9. Dubois D, Prade H (1998) Possibility Theory: Qualitative and Quantitative Aspects. In: Smets P (ed) Quantified representation of uncertainty and imprecision. Handbook of defeasible reasoning and uncertainty management systems, vol 1. Springer, Dordrecht

  10. Eziddin W (2012) Segmentation itérative d’images par propagation de connaissances dans le domaine possibiliste: application à la détection de tumeurs en imagerie mammographique. Traitement des images. Télécom Bretagne, Université de Bretagne Occidentale. Français

  11. Forgy E (1965) Cluster analysis of multivariate data: Efficiency vs. interpretability of classifications. Biometrics 21:768

    Google Scholar 

  12. Geman S, Geman D (1984) Stochastic relaxation, gibbs distributions, and the bayesian restoration of images. IEEE Trans on Patt Anal and Mach Intell 6(6):721–741

    Article  Google Scholar 

  13. Geman D, Geman S, Graffigne C, Dong P (1990) Boundary detection by constrained optimization. IEEE Trans on Patt Anal and Mach Intell 12(7):609–628

    Article  Google Scholar 

  14. Hatt M, Lamare F, Boussion N, Turzo A, Collet C, Salzenstein F, Roux C, Jarritt P, Carson K, Cheze-Le Rest C, Visvikis D (2007) Fuzzy hidden Markov chains segmentation for volume determination and quantitation in PET. Phys Med Biol 52:3467–3491

    Article  Google Scholar 

  15. Jenhani I, Ben Amor N, Elouedi Z, Benferhat S, Mellouli K (2007) Information Affinity: A New Similarity Measure for Possibilistic Uncertain Information. Lecture Notes in Computer Science, vol 4724. Springer, Berlin

  16. Khanfir Kallel I, Solaiman B (2017) Contextual Possibilistic Modeling Of Pixellic Knowledge For Tumor Segmentation In Mammographic Images. 3rd IEEE international conference on Advanced Technologies for Signal and Image Processing (ATSIP'2017), Fez

  17. Li BN, Chui CK, Chang S, Ong SH (2011) Integrating spatial fuzzy, clustering with level set methods for automated medical image segmentation. Comput Biol Med 41(1):1–10

    Article  Google Scholar 

  18. Long J, Shelhamer E, Darrell T (2015) Fully convolutional models for semantic segmentation. CVPR

  19. Lutton JL, Bonomi E (1988) Le recuit simulé. Pour la science 129:68–77 juillet

  20. McQueen J (1967) Some methods for classification and analysis of multivariate observations. In Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, p. 281-297

  21. Moiseev A, Snopova L, Kuznetsov S, Buyanova N, Elagin V, Sirotkina M, Kiseleva E, Matveev L, Zaitsev V, Feldchtein F, Zagaynova E, Gelikonov V, Gladkova N, Vitkin A, Gelikonov G (2017) Pixel classification method in optical coherence tomography for tumor segmentation and its complementary usage with OCT microangiography. J Biophotonics 11(4):e201700072. https://doi.org/10.1002/jbio.201700072

  22. Nie L, Wang M, Zha Z-J, Chua T-S (2012) Oracle in image search: A content-based approach to performance prediction. ACM Trans Inf Syst 30(2):13

    Article  Google Scholar 

  23. Otsu N (1978) A treshold selection method from gray-level histogram. IEEE Trans Systems Man Cybernet SMC 8:62–66

    Article  Google Scholar 

  24. Pieczynski W (2003) Modèles de Markov en traitement d’images. Traitement du Signal 20(3):255–277

    Google Scholar 

  25. Roy P, Goswami S, Chakraborty S, Azar AT, Dey N (2014) Image Segmentation Using Rough Set Theory: A Review. International Journal of Rough Sets and Data Analysis 1(2):62–74

    Article  Google Scholar 

  26. Shafer G (1976) A mathematical theory of evidence. Princeton University Press, Princeton, NJ

  27. Song JH, Cong W, Li J (2017) A Fuzzy C-means Clustering Algorithm for Image Segmentation Using Nonlinear Weighted Local Information. Journal of Information Hiding and Multimedia Signal Processing 8(9):1–11

    Google Scholar 

  28. Taroun A, Yang J (2011) Dempster-Shafer Theory of Evidence: Potential usage for decision making and risk analysis in construction project management. The Built & Human Environment 4(1):155–166

  29. Vannoorenberghe P (2003) Belief functions applied to information processing. Information Interaction Intelligence 3(2):9–45

    Google Scholar 

  30. Zhao F, Chen Y, Hou Y, He X (2017) Segmentation of blood vessels using rule-based and machinelearning based methods: a review. Multimedia Systems, Springer-Verlag GmbH Germany, part of Springer Nature

  31. Zhao W, Xianze X, Zhu Y, Xu F (2018) Active contour model based on local and global Gaussian fitting energy for medical image segmentation. Optik - International Journal for Light and Electron Optics 158:1160-1169

Download references

Acknowledgements

Imène Khanfir Kallel would like to address a deep thank to Professeor Eloi Bossé of McMaster University of Hamilton (Canada), for his scientific advices and support to technical content editing. Authors thank Professor Denis de BRUCQ of the Perception-System-Information (PSI) of the University of Rouen and the dermatological clinic of University Hospital of Rouen (France), for having provided a database of classified skin lesion images used in the present work. Authors acknowledge the technical assistance of Dr. Héla Fourati Mseddi, working in Medical Imagery Service of CHU Hédi Chaker Sfax, (Tunisia), for providing ground truth of the upcited images.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Imene Khanfir Kallel.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kallel, I.K., Almouahed, S., Alsahwa, B. et al. The use of contextual spatial knowledge for low-quality image segmentation. Multimed Tools Appl 78, 9645–9665 (2019). https://doi.org/10.1007/s11042-018-6540-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6540-1

Keywords

Navigation