Improvement of postal mail sorting system

  • Djamel GacebEmail author
  • Véronique Eglin
  • Frank Lebourgeois
  • Hubert Emptoz
Original Paper


An efficient mail sorting system is mainly based on an accurate optical recognition of the addresses on the envelopes. However, the localizing of the address block (ABL) should be done before the OCR recognition process. The location step is very crucial as it has a great impact on the global performance of the system. Consequently a good localizing step leads to a better recognition rate. The limits of current methods are mainly caused by modular linear architectures used for ABL and the lack of cooperation between modules: their performances greatly depend on each independent module performance. We are presenting in this paper a new approach for ABL based on a pyramidal data organization and on a hierarchical graph coloring for classification process. This new approach presents the advantage to guarantee a good coherence between different modules and it also reduces both the computation time and the rejection rate. The proposed method gives a very satisfying rate of 98% of good locations on a set of 750 envelope images.


Text location Physical segmentation Real time processing Business documents processing Graph coloring 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Ching-Huei, W., Palumbo, P.W., Srihari, S.N.: Object recognition in visually complex environments: an architecture for locating address blocks on mail pieces. Pattern Recognition, 9th International Conference, IEEE, vol. 1, pp. 365–367 (1988)Google Scholar
  2. 2.
    Viard-Gaudin, C., Barba, D.: A multi-resolution approach to extract the address block on flat mail pieces, ICASSP-91. International Conference, vol. 4, pp. 2701–2704 (1991)Google Scholar
  3. 3.
    Yu, B., Jain, A.K., Mohiuddin, M.: Address block location on complex mail pieces. Document Analysis and Recognition. Fourth International Conference, IEEE, vol. 2, pp. 897–901 (1997)Google Scholar
  4. 4.
    Jeong, S.H., Jang, S.I., Nam, Y.-S.: Locating destination address block in Korean mail images. ICPR 2004, IEEE, 17th International Conference, vol. 2, pp. 387–390 (2004)Google Scholar
  5. 5.
    Eiterer, L.F., Facon, J., Menoti, D.: Postal envelope address block location by fractal-based approach. Computer Graphics and Image Processing. 17th Brazilian Symposium, IEEE, pp. 90–97 (2004)Google Scholar
  6. 6.
    Otsu N.: A threshold selection method from grey-level histogram. IEEE Trans. Syst. Man Cybern. 9, 62–66 (1979)CrossRefGoogle Scholar
  7. 7.
    Sauvola, J. et al: Adaptive Document Binarization, ICDAR’97, vol. 1, pp. 147–152 (1997)Google Scholar
  8. 8.
    Gaceb, D., Lebourgeois, F., Eglin, V., Emptoz, H.: Contribution to the automatic recognition of business documents, 6p, IWFHR, La Baule, France (2006)Google Scholar
  9. 9.
    Regentova E., Latifi S., Deng S., Yao D.: An algorithm with reduced operations for connected components detection in ITU-T group 3/4 coded images. Pattern Anal. Mach. Intell. IEEE 24, 1039–1047 (2002)CrossRefGoogle Scholar
  10. 10.
    Pavlidis, Z., Zhou, J.: A page segmentation and classification. CVGIP92, vol. 54, no. 6, pp. 484–496 (1997)Google Scholar
  11. 11.
    Mullot, R.: book: Les documents écrits de la numérisation à l’indexation par le contenu, Editeur: Hermes science Publication, ISBN-10: 2746211432, p. 365 (2006)Google Scholar
  12. 12.
    Déforges O., Barba D.: A fast multiresolution text-line and non text line structures extraction and discrimination scheme for document image analysis. ICPR 94, pp. 134–138 (1994)Google Scholar
  13. 13.
    Drivas, D., Amin, A.: Page segmentation and classification utilising a bottom-up approach. Document Analysis and Recognition. ICDAR. Proceedings of the Third International Conference, vol. 2, pp. 610–614 (1995)Google Scholar
  14. 14.
    Shi, Z., Govindaraju, V.: Line separation for complex document images using fuzzy runlength, Document Image Analysis for Libraries, DIAL 2004. Proceedings, First International Workshop, pp. 306–312 (2004)Google Scholar
  15. 15.
    Wang S.-Y., Yagasaki T.: Block selection: a method for segmenting a page image of various editing styles, ICDAR. Proceedings of the Third International Conference on vol 1, pp. 128–133 (1995)Google Scholar
  16. 16.
    Agne, S., Rogger, M.: Benchmarking of Document Page Segmentation, Part of the IS&T/SPIE Conference on Document Recognition and Retrieval VII. San Jose, California, pp. 165–171 (2000)Google Scholar
  17. 17.
    Effantin B., Kheddouci H.: The b-chromatic number of power graphs. Discrete Math. Theor. Comput. Sci. (DMTCS) 6, 45–54 (2003)zbMATHMathSciNetGoogle Scholar
  18. 18.
    Effantin, B., Kheddouci, H.: a distributed algorithm for a b-coloring of a graph, the fourth international symposium on parallel and distributed processing and applications (ISPA’2006), serrento, Italy (2006)Google Scholar
  19. 19.
    Corteel, S., Valencia-Pabon, M., Vera, J.-C.: On approximating the b-chromatic number , Discrete Applied Mathematics archive, vol 146, pp. 106–110. ISSN:0166-218X (2005)Google Scholar
  20. 20.
    Paschos, V.: Book: Optimisation combinatoire 5: problèmes paradigmatiques et nouvelles problématiques, p. 270. Lavoisier, France (2007)Google Scholar
  21. 21.
    Elghazel, H., Hacid, M.-S., Khedddouci1 H., Dussauchoy, A.: A new clustering approach for symbolic data: algorithms and application to healthcare data. 22 éme journées bases de données avancées, BDA 2006, Lille. Actes On formal proceeding (2006)Google Scholar
  22. 22.
    Philipp-Foliguet, S.: Evaluation de la segmentation. Rapp. Tech. (2001)Google Scholar

Copyright information

© Springer-Verlag 2008

Authors and Affiliations

  • Djamel Gaceb
    • 1
    Email author
  • Véronique Eglin
    • 1
  • Frank Lebourgeois
    • 1
  • Hubert Emptoz
    • 1
  1. 1.LIRIS INSA de LyonVilleurbanne CedexFrance

Personalised recommendations