CFP last date
20 June 2024
Reseach Article

Article:An Automated Mail Sorter System using SVM Classifier

by Arun K.S, Jerin Thomas
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 32 - Number 6
Year of Publication: 2011
Authors: Arun K.S, Jerin Thomas
10.5120/3909-5488

Arun K.S, Jerin Thomas . Article:An Automated Mail Sorter System using SVM Classifier. International Journal of Computer Applications. 32, 6 ( October 2011), 27-31. DOI=10.5120/3909-5488

@article{ 10.5120/3909-5488,
author = { Arun K.S, Jerin Thomas },
title = { Article:An Automated Mail Sorter System using SVM Classifier },
journal = { International Journal of Computer Applications },
issue_date = { October 2011 },
volume = { 32 },
number = { 6 },
month = { October },
year = { 2011 },
issn = { 0975-8887 },
pages = { 27-31 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume32/number6/3909-5488/ },
doi = { 10.5120/3909-5488 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:18:29.382943+05:30
%A Arun K.S
%A Jerin Thomas
%T Article:An Automated Mail Sorter System using SVM Classifier
%J International Journal of Computer Applications
%@ 0975-8887
%V 32
%N 6
%P 27-31
%D 2011
%I Foundation of Computer Science (FCS), NY, USA
Abstract

This paper proposes an Automated Mail Sorter (AMS) system that scans a mail and interprets one of the imperative fields of the destination address, the pin code to sort the mails. The scanned document was segmented into different fields to extract the pin code. A general classifier for the recognition of pin-code digits written in English was then employed. The recognition system consists of a feature extractor and a classification network. The feature extracted was Hu moments and the classification network was the support vector machine using a polynomial kernel of order 2. Other classification networks such as the multi feature recognizer and decomposing network were also used, but SVM gave the maximum accuracy.

References
  1. K.Roy, S.Vaida,U.Pal,B. B. Chaudhuri and A.Belaid, “A System for Indian Postal Automation”, LORIA Research Center,B.P 239 54506, Nancy, France,2002 .
  2. Jameel Ahmed, Essha M. Alkhalifa, “Handwritten Digit Recognition Using an Optimizing Algorithm”, Proceedings of the 9th Internaional Conference on Neural Information Processing,2002.
  3. Jonathan Campbell, “Moment Invariant Shape Features: a brief explanation”, Letterkenny Institute of Technology, Ireland, 2004.
  4. Decong Yu, Lihong, Ma.”Digit Recognition Based on Multi-features”, IEEE Systems and Design Engineering Symposium, 2007.
  5. Venu Govindaraju and Sergey Tulyakoy, “Postal Address block location by contour clustering”, Proceedings of the Seventh International Conference on Document Analysis and Recognition,2003.
  6. TatsuhikoKagehiro, Masahi Koga, Hiroshi Sako and Hiromichi Fujisawa, Address Block Extraction by Bayesian Rule”, Proceedings of the 17th International Conference on Pattern Recognition, 2004.
  7. Adrian P. Whichello and Hong Yan, ”Locating Address Blocks and Postcodes in Mail-Piece Images”, Proceedings of the 14th International Conference on Pattern Recognition,1996.
  8. J.Weston and C. Watkin,”Multi-class Support Vector Machines”, Technical Report, Department of Computer Science, 1998.
  9. Dr Robert Sanderson, “Data Mining”, Dept. of Computer Science University of Liverpool, 2008.
  10. Bernard Lemaric, ”Practical Implementation of a Radial Basis Function Network for Handwritten Network for Handwritten Digit Recognition”, Proceedings of the Second National Conference on Document Analysis and Recognition,1993.
Index Terms

Computer Science
Information Sciences

Keywords

Support Vector Machine Hu Moments RLSA Algorithm Connected Component Labeling Region Labeling