Fractal-Based Approach for Segmentation of Address Block in Postal Envelopes

  • Luiz Felipe Eiterer
  • Jacques Facon
  • David Menoti
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3287)


In this paper, an address block segmentation approach based on fractal dimension FD is proposed. After computing the fractal dimension of each image pixel by the 2D variation procedure, a clustering technique based on K-means is used to label pixels into semantic objects. The evaluation of the efficiency is carried out from a total of 200 postal envelope images with no fixed position for the address block, postmark and stamp. A ground-truth strategy is used to achieve an objective comparison. Experiments showed significant and promising results. By using the 2D variation procedure for three ranges of neighbor window sizes (r= {3,5}, r= {3,5,7}, and r= {3,5,7,9}), the proposed approach reached a success rate over than 90% on average.


Fractal Dimension Texture Segmentation Digital Mammogram Address Block Local Fractal Dimension 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Yu, B., Jain, A., Mohiuddin, M.: Address block location on complex mail pieces. Technical Report MSUCPS:TR97-12, Dept. of Computer Science, Michigan State University (1997)Google Scholar
  2. 2.
    Yonekura, E., Facon, J.: Postal envelope segmentation by 2-d histogram clustering through watershed transform. In: ICDAR 2003, 7th International Conference on Document Analysis and Recognition, vol. 1, pp. 338–342 (2003)Google Scholar
  3. 3.
    Diayana, W.M., Larcher, J., Besar, R.: A comparison of clustered microcalcifications automated detection methods in digital mammogram. ICASSP, 385–388 (2003)Google Scholar
  4. 4.
    Ringler, A.: Texture segmentation by local fractal dimension as applied to oceanic search and rescue. In: IEEE ICICS, International Conference on Information Communications Signal Processing, vol. 2, pp. 975–979 (2003)Google Scholar
  5. 5.
    Samarbandu, J., Acharya, R., Hausmann, E., Allen, K.: Analysis of bone x-rays using morphological fractals. IEEE Transactions on Medical Imaging 12, 466–474 (1993)CrossRefGoogle Scholar
  6. 6.
    Chaudhuri, B., Sarkar, N., Kundu, P.: Improved fractal geometry based texture segmentation technique. IEE Proceedings 140, 233–241 (1993)Google Scholar
  7. 7.
    Dubuc, B., Quiniuo, J., Roques-Carmes, C., Tricot, C., Zucker, S.: Evaluating the fractal dimensions of profile. Phys. Rev. 39, 1500–1512 (1989)CrossRefMathSciNetGoogle Scholar
  8. 8.
    Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)Google Scholar
  9. 9.
    Jain, A., Dubes, R.: Algorithms for Clustering Data. Prentice Hall, Englewood Cliffs (1988)zbMATHGoogle Scholar
  10. 10.
    Fayad, U., Reina, C., Bradley, P.: Initialization of iterative refinement clustering algorithms. In: 4th KDD98- International Conference on Knowledge Discovery and Data Mining (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Luiz Felipe Eiterer
    • 1
  • Jacques Facon
    • 1
  • David Menoti
    • 1
    • 2
  1. 1.PUCPR-Pontifícia Universidade Católica do ParanáCuritibaBrazil
  2. 2.DCC Departamento de Ciência da ComputaçãoUFMG Universidade Federal de Minas GeraisBelo HorizonteBrazil

Personalised recommendations