Multi-level Modeling of Manuscripts for Authorship Identification with Collective Decision Systems

  • Salvador Godoy-Calderón
  • Edgardo M. Felipe-Riverón
  • Edith C. Herrera-Luna
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7441)


In the context of forensic and criminalistics studies the problem of identifying the author of a manuscript is generally expressed as a supervised-classification problem. In this paper a new approach for modeling a manuscript at the word and text line levels is presented. This new approach introduces an eclectic paradigm between texture-related and structure-related modeling approaches. Compared to previously published works, the proposed method significantly reduces the number and complexity of the text-features to be extracted from the text. Extensive experimentation with the proposed model shows it to be faster and easier to implement than other models, making it ideal for extensive use in forensic and criminalistics studies.


Collective decision Author identification Manuscript text Supervised pattern recognition 


  1. 1.
    Srihari, S.N., Cha, S.-H., Arora, H., Lee, S.: Individuality of Handwriting. Journal of Forensic Sciences 47(4), Paper ID JFS2001227-474 (2001)Google Scholar
  2. 2.
    Pecharromán-Balbás, S.: Reconocimiento de escritor independiente de texto basado en características de textura. Tesis doctoral. Escuela Politécnica Superior, Universidad Autónoma de Madrid (2007)Google Scholar
  3. 3.
    Bensefia, A., Paquet, T., Heutte, L.: A writer identification and verification system. Pattern Recognition Letters 26, 2080–2092 (2005)CrossRefGoogle Scholar
  4. 4.
    Srihari, S.N.: Recognition of handwritten and machine-printed text for postal address interpretation. Pattern Recognition Letters 14(4), 291–302 (1993)CrossRefGoogle Scholar
  5. 5.
    Said, H., Tan, T., Baker, K.: Personal Identification Based on Handwriting. Pattern Recognition 33(1), 149–160 (2000)CrossRefGoogle Scholar
  6. 6.
    Cover, T.M., Hart, P.E.: Nearest neighbour pattern classification. IEEE Trans. Inform. Theory, IT-13(1), 21–27 (1967)Google Scholar
  7. 7.
    Zois, E., Anastassopoulos, V.: Morphological waveform coding for writer identification. Pattern Recognition 33(3), 385–398 (2000)CrossRefGoogle Scholar
  8. 8.
    Pervouchine, V., Leedham, G.: Extraction and analysis of forensic document examiner features used for writer identification. Pattern Recognition 40, 1004–1013 (2007)zbMATHCrossRefGoogle Scholar
  9. 9.
    Hertel, C., Bunke, H.: A Set of Novel Features for Writer Identification. In: Proc. Fourth Int’l Conf. Audio and Video-Based Biometric Person Authentication, pp. 679–687 (2003)Google Scholar
  10. 10.
    Plamondon, R., Srihari, S.N.: On-line and off-line handwriting recognition: A comprehensive survey. IEEE Transactions on Pattern Analysis and Machine Intelligence 22, 63–84 (2000)CrossRefGoogle Scholar
  11. 11.
    Zimmermann, M., Bunke, H.: Automatic segmentation of the IAM off-line handwritten {English} text database. In: 16th International Conf. on Pattern Recognition, Canada, vol. 4, pp. 35–39 (2002)Google Scholar
  12. 12.
    Srihari, S.N.: Handwriting identification: research to study validity of individuality of handwriting and develop computer-assisted procedures for comparing handwriting. University of Buffalo, U.S.A. Center of Excellence for Document Analysis and Recognition. Tech. Rep. CEDAR-TR-01-1 (2001)Google Scholar
  13. 13.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. Sys., Man., Cyber. 9, 62–66 (1979)CrossRefGoogle Scholar
  14. 14.
    Khashman, A., Sekeroglu, B.: A Novel Thresholding Method for Text Separation and Document Enhancement. In: Proceedings of the 11th Pan-Hellenic Conference in Informatics, Greece, pp. 324–330 (2007)Google Scholar
  15. 15.
    Herrera-Luna, E., Felipe-Riverón, E., Godoy-Calderón, S.: A supervised algorithm with a new differentiated-weighting scheme for identifying the author of a handwritten text. Pattern Recognition Letters 32(2), 1139–1144 (2011)CrossRefGoogle Scholar
  16. 16.
    Marti, U.V., Messerli, R., Bunke, H.: Writer identification using text line based features. In: Proc. ICDAR 2001, pp. 101–105 (2001)Google Scholar
  17. 17.
    Louloudis, G., Gatos, B., Pratikakis, I., Halatsis, C.: Text line and word segmentation of handwritten documents. Pattern Recognition 42, 3169–3183 (2009)zbMATHCrossRefGoogle Scholar
  18. 18.
    Bertolami, R., Bunke, H.: Hidden Markov model-based ensemble methods for offline handwritten text line recognition. Pattern Recognition 41, 3452–3460 (2008)zbMATHCrossRefGoogle Scholar
  19. 19.
    Vamvakas, G., Gatos, B., Perantonis, S.J.: Handwritten character recognition through two-stage foreground sub-sampling. Pattern Recognition 43, 2807–2816 (2010)zbMATHCrossRefGoogle Scholar
  20. 20.
    Jou, C., Lee, H.C.: Handwritten numeral recognition based on simplified structural classification and fuzzy memberships. Expert Systems with Applications 36, 11858–11863 (2009)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Salvador Godoy-Calderón
    • 1
  • Edgardo M. Felipe-Riverón
    • 1
  • Edith C. Herrera-Luna
    • 1
  1. 1.Center for Computing ResearchNational Polytechnic InstituteGustavo A MaderoMéxico

Personalised recommendations