Advertisement

Superpixel Based Segmentation of Historical Document Images Using a Multiscale Texture Analysis

  • Emna SoyedEmail author
  • Ramzi Chaieb
  • Karim Kalti
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 146)

Abstract

In this paper, a superpixel based segmentation of Historical Document Images (HDIs) using multiscale texture analysis is proposed. A Simple Linear Iterative Clustering (SLIC) superpixel technique and Kmeans classifier are applied in order to separate the input image into background and foreground superpixels. The foreground superpixels are characterized by the standard deviation and the mean of the Gabor features. These features are extracted in a multiscale fashion to adapt to the variability of the textures that may be present in HDIs. Text/graphic separation is then performed by applying a classification of the foreground superpixels for each texture analysis scale followed by a merging step of the obtained classification results. Since the classification results depend on the used classifier, a comparative study is performed for supervised (Support Vector Machine (SVM), K-Nearest Neighbors (KNN)) and unsupervised (Kmeans, Fuzzy C-Means (FCM)) techniques. Experiments show the effectiveness of our proposed method especially when compared with similar work in the literature.

Keywords

Segmentation of Historical Document Images Multiscale texture analysis SLIC superpixel Gabor features Merging classification results 

References

  1. 1.
    Loussaief, S., Abdelkrim, A.: Machine learning framework for image classification. In: 2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), pp. 58–61. IEEE (2016)Google Scholar
  2. 2.
    El Bazzi, M., Mammass, D., Zaki, T., Ennaji, A.: A graph based method for Arabic document indexing. In: 2016 7th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), pp. 308–312. IEEE (2016)Google Scholar
  3. 3.
    Coustaty, M., Raveaux, R., Ogier, J.-M.: Historical document analysis: a review of French projects and open issues. In: 2011 19th European Signal Processing Conference, pp. 1445–1449. IEEE (2011)Google Scholar
  4. 4.
    Jiang, H.: Linear solution to scale invariant global figure ground separation. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 678–685. IEEE (2012)Google Scholar
  5. 5.
    Li, Z., Wu, X.-M., Chang, S.-F.: Segmentation using superpixels: a bipartite graph partitioning approach. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 789–796. IEEE (2012)Google Scholar
  6. 6.
    Cohen, R., Asi, A., Kedem, K., El-Sana, J., Dinstein, I.: Robust text and drawing segmentation algorithm for historical documents. In: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing, pp. 110–117. ACM (2013)Google Scholar
  7. 7.
    Garz, A., Sablatnig, R., Diem, M.: Layout analysis for historical manuscripts using sift features. In: 2011 International Conference on Document Analysis and Recognition (ICDAR), pp. 508–512. IEEE (2011)Google Scholar
  8. 8.
    Mehri, M., Sliti, N., Héroux, P., Gomez-Krämer, P., Amara, N.E.B., Mullot, R.: Use of SLIC superpixels for ancient document image enhancement and segmentation. In: SPIE/IS&T Electronic Imaging, p. 940205. International Society for Optics and Photonics (2015)Google Scholar
  9. 9.
    Mehri, M., Nayef, N., Héroux, P., Gomez-Krämer, P., Mullot, R.: Learning texture features for enhancement and segmentation of historical document images. In: Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing, pp. 47–54. ACM (2015)Google Scholar
  10. 10.
    Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2274–2282 (2012)CrossRefGoogle Scholar
  11. 11.
    Ursani, A.A., Kpalma, K., Ronsin, J.: Texture features based on Fourier transform and Gabor filters: an empirical comparison. In: International Conference on Machine Vision, ICMV 2007, pp. 67–72. IEEE (2007)Google Scholar
  12. 12.
    Mehri, M., Gomez-Krämer, P., Héroux, P., Boucher, A., Mullot, R.: Texture feature evaluation for segmentation of historical document images. In: Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing, pp. 102–109. ACM (2013)Google Scholar
  13. 13.
    Raju, S.S., Pati, P.B., Ramakrishnan, A.: Text localization and extraction from complex color images. In: International Symposium on Visual Computing, pp. 486–493. Springer (2005)Google Scholar
  14. 14.
    Charrada, M.A., Amara, N.E.B.: Texture approach for nets extraction application to old Arab newspapers images structuring. In: 2012 3rd International Conference on Image Processing Theory, Tools and Applications (IPTA), pp. 212–216. IEEE (2012)Google Scholar
  15. 15.
    Zhong, G., Cheriet, M.: Image patches analysis for text block identification. In: 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA), pp. 1241–1246. IEEE (2012)Google Scholar
  16. 16.
    Doermann, D., Zotkina, E., Li, H.: GEDI–a groundtruthing environment for document images. In: Ninth IAPR International Workshop on Document Analysis Systems (DAS 2010) (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.LATIS - Laboratory of Advanced Technology and Intelligent Systems, ENISoSousse UniversitySousseTunisia

Personalised recommendations