Advertisement

Recognition of Numeric Postal Codes from Multi-script Postal Address Blocks

  • Subhadip Basu
  • Nibaran Das
  • Ram Sarkar
  • Mahantapas Kundu
  • Mita Nasipuri
  • Dipak Kumar Basu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5909)

Abstract

The objective of the current work is to recognize postal codes written in Roman, Devanagari, Bangla and Arabic scripts. In the first stage 25 unique digit patterns are identified from the handwritten numeral patterns of the said four scripts. A script independent unified pattern classifier is then designed to classify any digit pattern of thesescripts into one of the 25 classes. In the next stage a rule-based script inference engine infers about the script of the numeric string, that invokes one of the four script specific classifiers. The average script-inference accuracy over a six digit numeric string is observed as 95.1% and the best recognition rates for the four script specific digit classifiers are obtained as 96.10%, 94.40%, 96.45 % and 95.60% respectively.

Keywords

OCR script-identification classification postal automation 

References

  1. 1.
    Sinha, S., Pal, U., Chaudhuri, B.B.: Word–Wise Script Identification from Indian Documents. In: Marinai, S., Dengel, A.R. (eds.) DAS 2004. LNCS, vol. 3163, pp. 310–321. Springer, Heidelberg (2004)Google Scholar
  2. 2.
    Roy, K., et al.: A System for Wordwise Handwritten Script Identification for Indian Postal Automation. In: IEEE INDICON 2004, pp. 266–271 (2004)Google Scholar
  3. 3.
    Zhou, L., Lu, Y., Tan, C.-L.: Bangla/English Script Identification Based on Analysis of Connected Component Profiles. In: Bunke, H., Spitz, A.L. (eds.) DAS 2006. LNCS, vol. 3872, pp. 243–254. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  4. 4.
    Roy, K., et al.: A System towards Indian Postal Automation. In: Proc. of the 9th IWFHR, pp. 361–367 (2004)Google Scholar
  5. 5.
    Roy, K., et al.: A System for Indian Postal Automation. In: Proc. of the 8th ICDAR (2005)Google Scholar
  6. 6.
    Basu, S., Chaudhuri, C., Kundu, M., Nasipuri, M., Basu, D.K.: A Two-Pass Approach to Pattern Classification. In: Pal, N.R., Kasabov, N., Mudi, R.K., Pal, S., Parui, S.K. (eds.) ICONIP 2004. LNCS, vol. 3316, pp. 781–786. Springer, Heidelberg (2004)Google Scholar
  7. 7.
    Basu, S., Sarkar, R., Das, N., Kundu, M., Nasipuri, M., Basu, D.K.: Handwritten Bangla digit recognition using classifier combination through DS technique. In: Pal, S.K., Bandyopadhyay, S., Biswas, S. (eds.) PReMI 2005. LNCS, vol. 3776, pp. 236–241. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  8. 8.
    Pal, U., et al.: Handwritten Numeral Recognition of Six Popular Indian Scripts. In: ICDAR 2007, pp. 749–753 (2007)Google Scholar
  9. 9.
    Wen, Y., et al.: Handwritten Bangla numeral recognition system and its application to postal automation. Pattern Recognition 40(1), 99–107 (2007)zbMATHCrossRefGoogle Scholar
  10. 10.
    Basu, S., et al.: Recognition of Pincodes from Indian Postal Documents. Soft Computing, 239–245Google Scholar
  11. 11.
    Basu, S., et al.: A Hierarchical Approach to Recognition of Handwritten Bangla Characters. Pattern Recognition 42(7), 1467–1484 (2009)zbMATHCrossRefGoogle Scholar
  12. 12.
    Nilson, N.J.: Principles of Artifcial Intelligence, pp. 21–22. Springer, HeidelbergGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Subhadip Basu
    • 1
  • Nibaran Das
    • 1
  • Ram Sarkar
    • 1
  • Mahantapas Kundu
    • 1
  • Mita Nasipuri
    • 1
  • Dipak Kumar Basu
    • 1
    • 2
  1. 1.Computer Science & Engineering DepartmentJadavpur UniversityKolkataIndia
  2. 2.A.I.C.T.E. Emeritus Fellow 

Personalised recommendations