Multimedia Tools and Applications

, Volume 55, Issue 3, pp 483–506 | Cite as

Automatic segmentation of digitalized historical manuscripts

  • Costantino GranaEmail author
  • Daniele Borghesani
  • Rita Cucchiara


The artistic content of historical manuscripts provides a lot of challenges in terms of automatic text extraction, picture segmentation and retrieval by similarity. In particular this work addresses the problem of automatic extraction of meaningful pictures, distinguishing them from handwritten text and floral and abstract decorations. The proposed solution firstly employs a circular statistics description of a directional histogram in order to extract text. Then visual descriptors are computed over the pictorial regions of the page: the semantic content is distinguished from the decorative parts using color histograms and a novel texture feature called Gradient Spatial Dependency Matrix. The feature vectors are finally processed using an embedding procedure which allows increased performance in later SVM classification. Results for both feature extraction and embedding based classification are reported, supporting the effectiveness of the proposal on high resolution replicas of artistic manuscripts.


Manuscript Image segmentation Texture analysis 


  1. 1.
    Barbu A Learning real-time MRF inference for image denoising. In: Computer vision and pattern recognitionGoogle Scholar
  2. 2.
    Bigun J, Bhattacharjee SK, Michel S (1996) In: Orientation radiograms for image retrieval: an alternative to segmentation, vol 3, pp 346–350Google Scholar
  3. 3.
    Bishop C (2006) Pattern recognition and machine learning. SpringerGoogle Scholar
  4. 4.
    Chen N, Blostein D (2007) A survey of document image classification: problem statement, classifier architecture and performance evaluation. Int J Doc Anal Recog 10:1–16zbMATHCrossRefGoogle Scholar
  5. 5.
    Crouse MS, Nowak RD, Baraniuk RG (1998) Wavelet-based statistical signal processing using hidden Markov models. IEEE Trans Signal Process 46:886–902MathSciNetCrossRefGoogle Scholar
  6. 6.
    Diligenti M, Frasconi P, Gori M (2003) Hidden tree Markov models for document image classification. IEEE Trans Pattern Anal Mach Intell 25:519–523CrossRefGoogle Scholar
  7. 7.
    Fataicha Y, Cheriet M, Nie J, et al (2002) Content analysis in document images: a scale Space approach. In: International conference on pattern recognition, vol 3. IEEE Computer Society, pp 335–338Google Scholar
  8. 8.
    Gill G (1981) Evaluation and inversion of the ratios of modified Bessel functions, \(I_0\left(x\right)/I_1\left(x\right)\) and \(I_{1.5}\left(x\right)/I_{0.5}\left(x\right)\). ACM Trans Math Softw 7:199–208CrossRefGoogle Scholar
  9. 9.
    Grana C, Vezzani R, Cucchiara R (2007) Enhancing HSV histograms with achromatic points detection for video retrieval. In: International conference on image and video retrieval, pp 302–308Google Scholar
  10. 10.
    Grana C, Borghesani D, Cucchiara R (2008) Describing texture directions with Von Mises distributions. In: International conference on pattern recognitionGoogle Scholar
  11. 11.
    Grana C, Borghesani D, Cucchiara R (2009) Fast block based connected components labeling. In: Proceedings of the IEEE international conference on image processing. Cairo, EgyptGoogle Scholar
  12. 12.
    Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3:610–621CrossRefGoogle Scholar
  13. 13.
    Hjaltason G, Samet H (2003) Properties of Embedding Methods for Similarity Searching in Metric Spaces. IEEE Transactions on Pattern Analysis and Machine Intelligence 25:530–549.CrossRefGoogle Scholar
  14. 14.
    Hu J, Kashi R, Wilfong R (1999) Document classification using layout analysis. In: International workshop on database and expert systems applications. IEEE Computer Society, pp 556–560Google Scholar
  15. 15.
    Jain A, Dubes R (1988) Algorithms for clustering data. Prentice-Hall, IncGoogle Scholar
  16. 16.
    Joachims T (1998) Text categorization with support vector machines: learning with many relevant features. In: European conference on machine learning. Springer, pp 137–142Google Scholar
  17. 17.
    Joachims T (2002) Learning to classify text using support vector machines: methods, theory, and algorithms. Kluwer Academic Publishers/SpringerGoogle Scholar
  18. 18.
    Journet N, Ramel J, Mullot R et al (2008) Document image characterization using a multiresolution analysis of the texture: application to old documents. Int J Doc Anal Recog 11:9–18CrossRefGoogle Scholar
  19. 19.
    Kavallieratou E (2005) A binarization algorithm specialized on document images and photos. In: International conference on document analysis and recognition. IEEE Computer Society, pp 463–467Google Scholar
  20. 20.
    Kitamoto A, Onishi M, Ikezaki T, et al (2006) Digital bleaching and content extraction for the digital archive of rare books. In: International conference on document image analysis for libraries. IEEE Computer Society, pp 133–144Google Scholar
  21. 21.
    Kittler J, Illingworth J (1985) Relaxation labelling algorithms—a review. Image Vis Comput 3:206–216CrossRefGoogle Scholar
  22. 22.
    Konidaris T, Gatos B, Ntzios K, et al (2007) Keyword-guided word spotting in historical printed documents using synthetic data and user feedback. Int J Doc Anal Recog 9:167–177CrossRefGoogle Scholar
  23. 23.
    Le Bourgeois F, Emptoz H (2007) DEBORA: Digital accEss to BOoks of the RenAissance. Int J Doc Anal Recog 9:193–221CrossRefGoogle Scholar
  24. 24.
    Le Bourgeois F, Trinh E, Allier B, et al (2004) Document images analysis solutions for digital libraries. In: International conference on document image analysis for libraries. IEEE Computer Society, pp 2–24Google Scholar
  25. 25.
    Meng G, Zheng N, Song Y, et al (2007) Document images retrieval based on multiple features combination. In: International conference on document analysis and recognition, vol 1. IEEE Computer Society, pp 143–147Google Scholar
  26. 26.
    Nagy G (2000) Twenty years of document image analysis in PAMI. IEEE Trans Pattern Anal Mach Intell 22:38–62CrossRefGoogle Scholar
  27. 27.
    Nicolas S, Dardenne J, Paquet T, et al (2007) Document image segmentation using a 2D conditional random field model. In: International conference on document analysis and recognition, vol 1, pp 407–411Google Scholar
  28. 28.
    Ogier J, Tombre K (2006) Madonne: document image analysis techniques for cultural heritage documents. In: Digital cultural heritage. Proceedings of 1st EVA conference, Oesterreichische Computer Gesellschaft, pp 107–114Google Scholar
  29. 29.
    Pekalska E, Duin RPW (2002) Dissimilarity representations allow for building good classifiers. Pattern Recogn Lett 23:943–956zbMATHCrossRefGoogle Scholar
  30. 30.
    Prati A, Calderara S, Cucchiara R (2008) Using circular statistics for trajectory analysis. In: International conference on image and video retrieval, pp 1–8Google Scholar
  31. 31.
    Ramel J, Busson S, Demonet M (2006) AGORA: the interactive document image analysis tool of the BVH project. In: International conference on document image analysis for libraries, pp 145–155Google Scholar
  32. 32.
    Sezgin M, Sankur B (2004) Survey over image thresholding techniques and quantitative performance evaluation. J Electron Imaging 13:146–168CrossRefGoogle Scholar
  33. 33.
    Shih FY, Cheng S (2005) Automatic seeded region growing for color image segmentation. Image Vis Comput 23:877–886CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2010

Authors and Affiliations

  • Costantino Grana
    • 1
    Email author
  • Daniele Borghesani
    • 1
  • Rita Cucchiara
    • 1
  1. 1.Università degli Studi di Modena e Reggio EmiliaModenaItaly

Personalised recommendations