A Recognition Method of Handprinted Thai Characters by Local Features

Pipat HIRANVANICHAKORN; Takeshi AGUI; Masayuki NAKAJIMA

A Recognition Method of Handprinted Thai Characters by Local Features

Pipat HIRANVANICHAKORN, Takeshi AGUI, Masayuki NAKAJIMA

Full Text Views

0

Cite this

Summary :

A recognition method of handprinted Thai characters by using local features is described. In the method, Freeman chain code and directional differences of contour tracing are utilized for extracting concavities and convexities of characters. Several local features are used to calculate similarities between arc portions and similarity between characters. Similar arcs are detected from characters of different categories to make a dictionary of arcs. Then, a dictionary of characters containing lists of names of character arcs is made to obtain a compact dictionary of models. By applying the method to 69 categories (828 data) of Thai characters, a recognition rate of 99.3% for learning data, and a recognition rate of 88.9% for test data have been obtained.

Publication: IEICE TRANSACTIONS on transactions Vol.E68-E No.2 pp.83-90

Publication Date: 1985/02/25

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Data Processing

Authors

Pipat HIRANVANICHAKORN
Takeshi AGUI
Masayuki NAKAJIMA

Keyword

Cite this

Copy

Pipat HIRANVANICHAKORN, Takeshi AGUI, Masayuki NAKAJIMA, "A Recognition Method of Handprinted Thai Characters by Local Features" in IEICE TRANSACTIONS on transactions, vol. E68-E, no. 2, pp. 83-90, February 1985, doi: .
Abstract: A recognition method of handprinted Thai characters by using local features is described. In the method, Freeman chain code and directional differences of contour tracing are utilized for extracting concavities and convexities of characters. Several local features are used to calculate similarities between arc portions and similarity between characters. Similar arcs are detected from characters of different categories to make a dictionary of arcs. Then, a dictionary of characters containing lists of names of character arcs is made to obtain a compact dictionary of models. By applying the method to 69 categories (828 data) of Thai characters, a recognition rate of 99.3% for learning data, and a recognition rate of 88.9% for test data have been obtained.
URL: https://global.ieice.org/en_transactions/transactions/10.1587/e68-e_2_83/_p

Copy

@ARTICLE{e68-e_2_83,
author={Pipat HIRANVANICHAKORN, Takeshi AGUI, Masayuki NAKAJIMA, },
journal={IEICE TRANSACTIONS on transactions},
title={A Recognition Method of Handprinted Thai Characters by Local Features},
year={1985},
volume={E68-E},
number={2},
pages={83-90},
abstract={A recognition method of handprinted Thai characters by using local features is described. In the method, Freeman chain code and directional differences of contour tracing are utilized for extracting concavities and convexities of characters. Several local features are used to calculate similarities between arc portions and similarity between characters. Similar arcs are detected from characters of different categories to make a dictionary of arcs. Then, a dictionary of characters containing lists of names of character arcs is made to obtain a compact dictionary of models. By applying the method to 69 categories (828 data) of Thai characters, a recognition rate of 99.3% for learning data, and a recognition rate of 88.9% for test data have been obtained.},
keywords={},
doi={},
ISSN={},
month={February},}

Copy

TY - JOUR
TI - A Recognition Method of Handprinted Thai Characters by Local Features
T2 - IEICE TRANSACTIONS on transactions
SP - 83
EP - 90
AU - Pipat HIRANVANICHAKORN
AU - Takeshi AGUI
AU - Masayuki NAKAJIMA
PY - 1985
DO -
JO - IEICE TRANSACTIONS on transactions
SN -
VL - E68-E
IS - 2
JA - IEICE TRANSACTIONS on transactions
Y1 - February 1985
AB - A recognition method of handprinted Thai characters by using local features is described. In the method, Freeman chain code and directional differences of contour tracing are utilized for extracting concavities and convexities of characters. Several local features are used to calculate similarities between arc portions and similarity between characters. Similar arcs are detected from characters of different categories to make a dictionary of arcs. Then, a dictionary of characters containing lists of names of character arcs is made to obtain a compact dictionary of models. By applying the method to 69 categories (828 data) of Thai characters, a recognition rate of 99.3% for learning data, and a recognition rate of 88.9% for test data have been obtained.
ER -