• DocumentCode
    2637555
  • Title

    Destination address interpretation for automating the sorting process of Indian Postal System

  • Author

    Prasanna, PSri Rama ; Balaji, S. ; Khezhie, Thejavor Haralu ; Vasanthanayaki, C. ; Annadurai, S.

  • Author_Institution
    Dept. of Electron. & Commun. Eng., Gov. Coll. of Technol., Coimbatore, India
  • Volume
    2
  • fYear
    2003
  • fDate
    15-17 Oct. 2003
  • Firstpage
    858
  • Abstract
    While most Indian industries are in the process of automation, the Indian Postal System is still using manual mail sorting and processing. We propose an automated system to reduce the mail sorting time and rule out human errors. Our automatic mail processor (AMP) scans a mail item and interprets the imperative fields of the destination address, such as the pin code, city name, locality name and the street name. The interpreted address is subsequently converted into a delivery point code (DPC), which is a 12 digit number. The DPC is printed on to the mail in the form of a barcode which can be read by a low-cost machine. By converting the destination address into a barcode, all future sorting processes can be accomplished by a mechanical machine sorter, which can sort the mail according to the barcode. The AMP comprises of five modules namely preprocessing unit, address block location unit, line and word separation unit, address parsing and recognition unit and DPC generation unit. The address parser detects the location of the fields using a heuristic procedure. The recognition system is accomplished by representing the characters in the form of chain codes, and using their Fourier descriptors for alphanumeric matching with the aid of a neural network. The DPC is then generated using the pin code (6 digits) and the street code. A database is used in this step to assign 5 digit codes for street names. The DPC is then bar-coded and printed on to the mail.
  • Keywords
    automation; bar codes; character recognition; image processing; neural nets; postal services; Fourier descriptors; Indian Postal System; address block location; address parsing; address recognition; alphanumeric matching; automatic mail processor; barcode; chain codes; city name; delivery point code; destination address interpretation; locality name; mail sorting automation; neural network; pin code; preprocessing unit; street name; Automation; Communication industry; Educational institutions; Electronics industry; Government; Industrial electronics; Manuals; Pixel; Postal services; Sorting;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    TENCON 2003. Conference on Convergent Technologies for the Asia-Pacific Region
  • Print_ISBN
    0-7803-8162-9
  • Type

    conf

  • DOI
    10.1109/TENCON.2003.1273300
  • Filename
    1273300