This paper proposes a scheme which combines the conventional technique with a multi-level structure of Thai sentences for detection and segmentation for touching Thai printed characters. The proposed scheme solves problems of both horizontally and vertically touching characters. The complexity of a multi-level structure is employed to classify characters into three zones. The edge detection technique is applied to separate overlapping characters. Then, the horizontal touching characters are determined by using a statistical width of characters. The segmentation point of horizontal touching characters is determined using vertical projection combined with a statistical width of characters. The vertical touching characters are determined by considering the overlapping area of character boundary between zones. The height of line is used to separate the segment of vertical touching characters. Ambiguities are handle by using distinctive features of Thai characters. The effectiveness of the proposed scheme is tested with data from both newspapers and printed documents. The accuracy of 97 and 98 percents are obtained for newspaper and printed documents respectively.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Nucharee PREMCHAISWADI, Wichian PREMCHAISWADI, Seinosuke NARITA, "Segmentation of Horizontal and Vertical Touching Thai Characters" in IEICE TRANSACTIONS on Fundamentals,
vol. E83-A, no. 6, pp. 987-995, June 2000, doi: .
Abstract: This paper proposes a scheme which combines the conventional technique with a multi-level structure of Thai sentences for detection and segmentation for touching Thai printed characters. The proposed scheme solves problems of both horizontally and vertically touching characters. The complexity of a multi-level structure is employed to classify characters into three zones. The edge detection technique is applied to separate overlapping characters. Then, the horizontal touching characters are determined by using a statistical width of characters. The segmentation point of horizontal touching characters is determined using vertical projection combined with a statistical width of characters. The vertical touching characters are determined by considering the overlapping area of character boundary between zones. The height of line is used to separate the segment of vertical touching characters. Ambiguities are handle by using distinctive features of Thai characters. The effectiveness of the proposed scheme is tested with data from both newspapers and printed documents. The accuracy of 97 and 98 percents are obtained for newspaper and printed documents respectively.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e83-a_6_987/_p
Copy
@ARTICLE{e83-a_6_987,
author={Nucharee PREMCHAISWADI, Wichian PREMCHAISWADI, Seinosuke NARITA, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Segmentation of Horizontal and Vertical Touching Thai Characters},
year={2000},
volume={E83-A},
number={6},
pages={987-995},
abstract={This paper proposes a scheme which combines the conventional technique with a multi-level structure of Thai sentences for detection and segmentation for touching Thai printed characters. The proposed scheme solves problems of both horizontally and vertically touching characters. The complexity of a multi-level structure is employed to classify characters into three zones. The edge detection technique is applied to separate overlapping characters. Then, the horizontal touching characters are determined by using a statistical width of characters. The segmentation point of horizontal touching characters is determined using vertical projection combined with a statistical width of characters. The vertical touching characters are determined by considering the overlapping area of character boundary between zones. The height of line is used to separate the segment of vertical touching characters. Ambiguities are handle by using distinctive features of Thai characters. The effectiveness of the proposed scheme is tested with data from both newspapers and printed documents. The accuracy of 97 and 98 percents are obtained for newspaper and printed documents respectively.},
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - Segmentation of Horizontal and Vertical Touching Thai Characters
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 987
EP - 995
AU - Nucharee PREMCHAISWADI
AU - Wichian PREMCHAISWADI
AU - Seinosuke NARITA
PY - 2000
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E83-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 2000
AB - This paper proposes a scheme which combines the conventional technique with a multi-level structure of Thai sentences for detection and segmentation for touching Thai printed characters. The proposed scheme solves problems of both horizontally and vertically touching characters. The complexity of a multi-level structure is employed to classify characters into three zones. The edge detection technique is applied to separate overlapping characters. Then, the horizontal touching characters are determined by using a statistical width of characters. The segmentation point of horizontal touching characters is determined using vertical projection combined with a statistical width of characters. The vertical touching characters are determined by considering the overlapping area of character boundary between zones. The height of line is used to separate the segment of vertical touching characters. Ambiguities are handle by using distinctive features of Thai characters. The effectiveness of the proposed scheme is tested with data from both newspapers and printed documents. The accuracy of 97 and 98 percents are obtained for newspaper and printed documents respectively.
ER -