A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints
Summary :
This paper presents a model and its effect for on-line handwritten Japanese text recognition free from line-direction constraint and writing format constraint such as character writing boxes or ruled lines. The model evaluates the likelihood composed of character segmentation, character recognition, character pattern structure and context. The likelihood of character pattern structure considers the plausible height, width and inner gaps within a character pattern that appear in Chinese characters composed of multiple radicals (subpatterns). The recognition system incorporating this model separates freely written text into text line elements, estimates the average character size of each element, hypothetically segments it into characters using geometric features, applies character recognition to segmented patterns and employs the model to search the text interpretation that maximizes likelihood as Japanese text. We show the effectiveness of the model through recognition experiments and clarify how the newly modeled factors in the likelihood affect the overall recognition rate.
- Publication
- IEICE TRANSACTIONS on Information Vol.E88-D No.8 pp.1815-1822
- Publication Date
- 2005/08/01
- Publicized
- Online ISSN
- DOI
- 10.1093/ietisy/e88-d.8.1815
- Type of Manuscript
- Special Section PAPER (Special Section on Document Image Understanding and Digital Documents)
- Category
- On-line Text
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
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.
Cite this
Copy
Masaki NAKAGAWA, Bilan ZHU, Motoki ONUMA, "A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints" in IEICE TRANSACTIONS on Information,
vol. E88-D, no. 8, pp. 1815-1822, August 2005, doi: 10.1093/ietisy/e88-d.8.1815.
Abstract: This paper presents a model and its effect for on-line handwritten Japanese text recognition free from line-direction constraint and writing format constraint such as character writing boxes or ruled lines. The model evaluates the likelihood composed of character segmentation, character recognition, character pattern structure and context. The likelihood of character pattern structure considers the plausible height, width and inner gaps within a character pattern that appear in Chinese characters composed of multiple radicals (subpatterns). The recognition system incorporating this model separates freely written text into text line elements, estimates the average character size of each element, hypothetically segments it into characters using geometric features, applies character recognition to segmented patterns and employs the model to search the text interpretation that maximizes likelihood as Japanese text. We show the effectiveness of the model through recognition experiments and clarify how the newly modeled factors in the likelihood affect the overall recognition rate.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.8.1815/_p
Copy
@ARTICLE{e88-d_8_1815,
author={Masaki NAKAGAWA, Bilan ZHU, Motoki ONUMA, },
journal={IEICE TRANSACTIONS on Information},
title={A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints},
year={2005},
volume={E88-D},
number={8},
pages={1815-1822},
abstract={This paper presents a model and its effect for on-line handwritten Japanese text recognition free from line-direction constraint and writing format constraint such as character writing boxes or ruled lines. The model evaluates the likelihood composed of character segmentation, character recognition, character pattern structure and context. The likelihood of character pattern structure considers the plausible height, width and inner gaps within a character pattern that appear in Chinese characters composed of multiple radicals (subpatterns). The recognition system incorporating this model separates freely written text into text line elements, estimates the average character size of each element, hypothetically segments it into characters using geometric features, applies character recognition to segmented patterns and employs the model to search the text interpretation that maximizes likelihood as Japanese text. We show the effectiveness of the model through recognition experiments and clarify how the newly modeled factors in the likelihood affect the overall recognition rate.},
keywords={},
doi={10.1093/ietisy/e88-d.8.1815},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - A Model of On-line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints
T2 - IEICE TRANSACTIONS on Information
SP - 1815
EP - 1822
AU - Masaki NAKAGAWA
AU - Bilan ZHU
AU - Motoki ONUMA
PY - 2005
DO - 10.1093/ietisy/e88-d.8.1815
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2005
AB - This paper presents a model and its effect for on-line handwritten Japanese text recognition free from line-direction constraint and writing format constraint such as character writing boxes or ruled lines. The model evaluates the likelihood composed of character segmentation, character recognition, character pattern structure and context. The likelihood of character pattern structure considers the plausible height, width and inner gaps within a character pattern that appear in Chinese characters composed of multiple radicals (subpatterns). The recognition system incorporating this model separates freely written text into text line elements, estimates the average character size of each element, hypothetically segments it into characters using geometric features, applies character recognition to segmented patterns and employs the model to search the text interpretation that maximizes likelihood as Japanese text. We show the effectiveness of the model through recognition experiments and clarify how the newly modeled factors in the likelihood affect the overall recognition rate.
ER -
English
