Handwritten Postal Code Recognition by Neural Network --A Comparative Study --

Ahmad Fadzil ARIF  Hidekazu TAKAHASHI  Akira IWATA  Toshio TSUTSUMIDA  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E79-D    No.5    pp.443-449
Publication Date: 1996/05/25
Online ISSN: 
DOI: 
Print ISSN: 0916-8532
Type of Manuscript: Special Section PAPER (Special Issue on Character Recognition and Document Understanding)
Category: Comparative Study
Keyword: 
handwritten numeral recognition,  feature extraction,  neural network,  

Full Text: PDF>>
Buy this Article



Summary: 
This paper compares some popular character recognition techniques which have been proposed until today. 17 feature extraction methods and 4 neural network based recognition processes were used in handwritten numerals (postal codes) recognition. It was found that Weighted Direction Index Histogram, Peripheral Direction Contributivity Function and Expansion Cell feature extractions gave good results. As for the neural network recognition process, CombNET- and multi layer neural network showed good performances.