A Character-Structure-Guided Approach to Estimating Possible Orientations of a Rotated Isolated Online Handwritten Chinese Character

Author

He, Tingting ; Huo, Qiang

Author_Institution

Dept. of Comput. Sci., Univ. of Hong Kong, Hong Kong, China

fYear

2009

Firstpage

536

Lastpage

540

Abstract

This paper presents a character-structure-guided approach to estimating possible orientations of a rotated isolated online handwritten Chinese character. Using the estimated orientations, the original distorted sample can be transformed to a normal position, which can be recognized more accurately by using a classifier trained from normal-position samples. The effectiveness of this approach is demonstrated by recognizing rotated samples generated artificially from the popular Nakayosi and Kuchibue Japanese character databases, with average recognition accuracies of 96.05%, 97.35% and 99.13% on top-6, top-12, and top-100 candidates, respectively.

Keywords

feature extraction; handwritten character recognition; natural language processing; Kuchibue Japanese character database; Nakayosi Japanese character database; character recognition; character-structure-guided approach; rotated isolated online handwritten Chinese character; Asia; Character generation; Character recognition; Computer science; Databases; Feature extraction; Handwriting recognition; Histograms; Text analysis; Writing; Chinese character structure; handwriting recognition; orientation estimation;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2009. ICDAR '09. 10th International Conference on

Conference_Location

Barcelona

ISSN

1520-5363

Print_ISBN

978-1-4244-4500-4

Electronic_ISBN

1520-5363

Type

conf

DOI

10.1109/ICDAR.2009.84

Filename

5277600