A Lexicon-Driven Handwritten City-Name Recognition Scheme for Indian Postal Automation

Umapada PAL  Kaushik ROY  Fumitaka KIMURA 

Publication
IEICE TRANSACTIONS on Information and Systems  Vol.E92-D  No.5  pp.1146-1158
Publication Date: 2009/05/01
Online ISSN: 1745-1361
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Image Recognition, Computer Vision
Keyword: 
handwriting recognition,  cursive script recognition,  modified quadratic discriminant function,  Indian script,  postal automation, 

Full Text: PDF(1MB)

Summary: 
A lexicon-driven segmentation-recognition scheme on Bangla handwritten city-name recognition is proposed for Indian postal automation. In the proposed scheme, at first, binarization of the input document is done and then to take care of slanted handwriting of different individuals a slant correction technique is performed. Next, due to the script characteristics of Bangla, a water reservoir concept is applied to pre-segment the slant corrected city-names into possible primitive components (characters or its parts). Pre-segmented components of a city-name are then merged into possible characters to get the best city-name using the lexicon information. In order to merge these primitive components into characters and to find optimum character segmentation, dynamic programming (DP) is applied using total likelihood of the characters of a city-name as an objective function. To compute the likelihood of a character, Modified Quadratic Discriminant Function (MQDF) is used. The features used in the MQDF are mainly based on the directional features of the contour points of the components. We tested our system on 84 different Bangla city-names and 94.08% accuracy was obtained from the proposed system.