Skip to main content

Influence of normalization and color features on super-pixel classification: application to cytological image segmentation

Australasian Physical & Engineering Sciences in Medicine volume 42, pages 427–441 (2019)Cite this article

Abstract

Super-pixel feature extraction is a key problem to get an acceptable performance in color super-pixel classification. Given a color feature extraction problem, it is necessary to know which is the best approach to solve this problem. In the current work, we’re interested in the challenge of nucleus and cytoplasm automatic recognition in the cytological image. We propose an automatic process for white blood cells (WBC) segmentation using super-pixel classification. The process is divided into five steps. In first step, the color normalization is calculated. The super-pixels generation by Simple Linear Iterative Clustering algorithm is performed in the second step. In third step, the color property is used to achieve illumination invariance. In fourth step, color features are calculated on each super-pixel. Finally, supervised learning is realized to classify each super-pixel into nucleus and cytoplasm region. The present work rallied an exhaustive statistical evaluation of a very wide variety of the color super-pixel classification, with height normalization methods, four-color spaces and four feature extraction techniques. Normalization and color spaces slightly increase the average accuracy of super-pixel classification. Our experiments based to statistical comparison allow to conclude that comprehensive gray world normalized normalization is better than without normalization for super-pixel classification achieving the first positions in the Friedman ranking. RGB space is the best color spaces to be used in super-pixel feature extraction for nucleus and cytoplasm segmentation. For feature extraction, the learning methods work better on the first order statistics features for the automatic WBC segmentation.

This is a preview of subscription content, access via your institution.

Access options

Buy single article

Instant access to the full article PDF.

43,34 €

Price includes VAT (Finland)
Tax calculation will be finalised during checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

References

  1. Abu-Mostafa YS, Psaltis D (1984) Recognitive aspects of moment invariants. IEEE Trans Pattern Anal Mach Intell 6:698–706

    CAS  Article  Google Scholar 

  2. Achanta R, Shaji A, Smith K, Lucchi A, Fua P, Süsstrunk S (2012) Slic superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282

    Article  Google Scholar 

  3. Alata O, Burie JC, Moussa A, Fernandez-Maloigne C (2011) Choice of a pertinent color space for color texture characterization using parametric spectral analysis. Pattern Recognit 44(1):16–31

    Article  Google Scholar 

  4. Artan Y (2011) Interactive image segmentation using machine learning techniques. In: 2011 Canadian conference on computer and robot vision, pp 264–269. https://doi.org/10.1109/CRV.2011.42

  5. Bechar MEA, Settouti N, Barra V, Chikh MA (2018) Semi-supervised superpixel classification for medical images segmentation: application to detection of glaucoma disease. Multidimens Syst Signal Process 29(3):979–998. https://doi.org/10.1007/s11045-017-0483-y

    Article  Google Scholar 

  6. Benazzouz M, Baghli I, Chikh MA (2013) Microscopic image segmentation based on pixel classification and dimensionality reduction. Int J Imaging Syst Technol 23(1):22–28. http://dblp.uni-trier.de/db/journals/imst/imst23.html#BenazzouzBC13

  7. Borovec J, Svihlík J, Kybic J, Habart D (2017) Supervised and unsupervised segmentation using superpixels, model estimation, and graph cut. J Electron Imaging 26(6):61610

    Google Scholar 

  8. Boschetto D, Grisan E (2017) Superpixel-based classification of gastric chromoendoscopy images. In: Medical imaging: computer-aided diagnosis, SPIE, SPIE Proceedings, vol 10134, p 101340W

  9. Boyce JF, Hossack W (1983) Moment invariants for pattern recognition. Pattern Recognit Lett 1(5–6):451–456

    Article  Google Scholar 

  10. Cernadas E, Fernández-Delgado M, González-Rufino E, Carrión P (2017) Influence of normalization and color space to color texture classification. Pattern Recognit 61:120–138

    Article  Google Scholar 

  11. Cheng L, Ye N, Yu W, Cheah A (2011) Discriminative segmentation of microscopic cellular images. In: International conference on medical image computing and computer-assisted intervention. Springer, New York, pp 637–644

  12. Choi JY, Ro YM, Plataniotis KN (2012) Color local texture features for color face recognition. IEEE Trans Image Process 21(3):1366–1380

    Article  Google Scholar 

  13. Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30. http://dl.acm.org/citation.cfm?id=1248547.1248548

  14. Drimbarean A, Whelan PF (2001) Experiments in colour texture analysis. Pattern Recognit Lett 22(10):1161–1167

    Article  Google Scholar 

  15. Ebner M (2007) Color constancy, vol 6. Wiley, New York

    Google Scholar 

  16. Finlayson GD, Schiele B, Crowley JL (1998) Comprehensive colour image normalization. In: European conference on computer vision. Springer, New York, pp 475–490

  17. Forsythe J, Kurlin V (2017) Convex constrained meshes for superpixel segmentations of images. J Electron Imaging 26(6):61609

    Article  Google Scholar 

  18. Fulkerson B, Vedaldi A, Soatto S et al (2009) Class segmentation and object localization with superpixel neighborhoods. In: ICCV, Citeseer, vol 9, pp 670–677

  19. González-Rufino E, Carrión P, Cernadas E, Fernández-Delgado M, Domínguez-Petit R (2013) Exhaustive comparison of colour texture features and classification methods to discriminate cells categories in histological images of fish ovary. Pattern Recogn 46(9):2391–2407

    Article  Google Scholar 

  20. Gu L, Zheng Y, Bise R, Sato I, Imanishi N, Aiso S (2017) Semi-supervised learning for biomedical image segmentation via forest oriented super pixels(voxels). In: MICCAI

  21. He X, Zemel RS, Ray D (2006) Learning and incorporating top-down cues in image segmentation. In: European conference on computer vision. Springer, New York, pp 338–351

  22. Hoiem D, Efros AA, Hebert M (2005) Automatic photo pop-up. ACM Trans Graph 24(3):577–584

    Article  Google Scholar 

  23. Hu MK (1962) Visual pattern recognition by moment invariants. IRE Trans Inf Theory 8(2):179–187

    Article  Google Scholar 

  24. Irshad H, Veillard A, Roux L, Racoceanu D (2014) Methods for nuclei detection, segmentation, and classification in digital histopathology: a review-current status and future potential. IEEE Rev Biomed Eng 7:97–114

    Article  Google Scholar 

  25. Kakumanu P, Makrogiannis S, Bourbakis N (2007) A survey of skin-color modeling and detection methods. Pattern Recognit 40(3):1106–1122

    Article  Google Scholar 

  26. Kandaswamy U, Schuckers SA, Adjeroh D (2011) Comparison of texture analysis schemes under nonideal conditions. IEEE Trans Image Process 20(8):2260–2275

    Article  Google Scholar 

  27. Kandaswamy U, Adjeroh DA, Schuckers S, Hanbury A (2012) Robust color texture features under varying illumination conditions. IEEE Trans Syst Man Cybern Part B 42(1):58–68

    Article  Google Scholar 

  28. Levinshtein A, Dickinson SJ, Sminchisescu C (2009) Multiscale symmetric part detection and grouping. In: ICCV, pp 2162–2169

  29. Li Y, Sun J, Tang CK, Shum HY (2004) Lazy snapping. In: ACM transactions on graphics (ToG), vol 23. ACM, New York, pp 303–308

  30. Limare N, Lisani JL, Morel JM, Petro AB, Sbert C (2011) Simplest color balance. Image Process Line 1:297–315

    Google Scholar 

  31. Mäenpää T, Pietikäinen M (2004) Classification with color and texture: jointly or separately? Pattern Recognit 37(8):1629–1640

    Article  Google Scholar 

  32. Magaña-Tellez O, Vrigkas M, Nikou C, Kakadiaris IA (2018) SPICE: superpixel classification for cell detection and counting. In: VISIGRAPP (4: VISAPP). SciTePress, pp 485–490

  33. Mery D, Filbert D (2002) Classification of potential defects in automated inspection of aluminium castings using statistical pattern recognition. In: Proceedings of 8th European conference on non-destructive testing (ECNDT 2002), pp 17–21

  34. Nakamura K, Hong B (2017) Hierarchical image segmentation via recursive superpixel with adaptive regularity. J Electron Imaging 26(6):61602

    Article  Google Scholar 

  35. Nava R, Kybic J (2015) Supertexton-based segmentation in early drosophila oogenesis. In: ICIP. IEEE, pp 2656–2659

  36. Paschos G (2001) Perceptually uniform color spaces for color texture analysis: an empirical evaluation. IEEE Trans Image Process 10(6):932–937

    Article  Google Scholar 

  37. Ren X, Malik J (2003a) Learning a classification model for segmentation. In: Computer vision. Proceedings. Ninth IEEE international conference on. IEEE, pp 10–17

  38. Ren X, Malik J (2003b) Learning a classification model for segmentation. IEEE, p 10

  39. Schaefer G, Finlayson G, Hordley S, Tian G (2005) Illuminant and device invariant color using histogram equalization. Pattern Recognit 28:179–190

    Google Scholar 

  40. Vandenbroucke N, Macaire L, Postaire JG (2003) Color image segmentation by pixel classification in an adapted hybrid color space. application to soccer image analysis. Comput Vision Image Underst 90(2):190–216

    Article  Google Scholar 

  41. Vandenbroucke N, Busin L, Macaire L (2015) Unsupervised color-image segmentation by multicolor space iterative pixel classification. J Electron Imaging 24(2):023032–023032

    Article  Google Scholar 

  42. Varma M, Zisserman A (2005) A statistical approach to texture classification from single images. Int J Comput Vis 62(1):61–81

    Article  Google Scholar 

  43. Varma M, Zisserman A (2009) A statistical approach to material classification using image patch exemplars. IEEE Trans Pattern Anal Mach Intell 31(11):2032–2047

    Article  Google Scholar 

  44. Wu W, Chen AY, Zhao L, Corso JJ (2014) Brain tumor detection and segmentation in a crf (conditional random fields) framework with pixel-pairwise affinity and superpixel-level features. Int J Comput Assist Radiol Surg 9(2):241–253

    Article  Google Scholar 

  45. Xu J, Ishikawa H, Wollstein G, Schuman JS (2011) 3d optical coherence tomography super pixel with machine classifier analysis for glaucoma detection. In: EMBC. IEEE, pp 3395–3398

  46. Zuiderveld K (1994) Contrast limited adaptive histogram equalization. In: Graphics gems IV. Academic Press Professional, Inc., New York, pp 474–485

Download references

Funding

No funding was received.

Author information

Affiliations

  1. CNRS, Centrale Marseille, Aix Marseille Univ, Institut Fresnel UMR 7249, 13013, Marseille, France

    Mohammed El Amine Bechar & Mouloud Adel

  2. Biomedical Engineering Laboratory GBM, Tlemcen University, Tlemcen, Algeria

    Mohammed El Amine Bechar, Nesma Settouti, Mostafa El Habib Daho & Mohammed Amine Chikh

Authors
  1. Mohammed El Amine Bechar
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Nesma Settouti
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mostafa El Habib Daho
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mouloud Adel
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mohammed Amine Chikh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mohammed El Amine Bechar.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethical approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed consent

Not applicable.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Bechar, M.E.A., Settouti, N., Daho, M.E.H. et al. Influence of normalization and color features on super-pixel classification: application to cytological image segmentation. Australas Phys Eng Sci Med 42, 427–441 (2019). https://doi.org/10.1007/s13246-019-00735-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-019-00735-8

Keywords

  • Super-pixel classification
  • Image normalization
  • Color space
  • Feature extraction
  • Supervised classification
  • White blood cells