This paper presents a semi-incremental recognition method for on-line handwritten Japanese text and its evaluation. As text becomes longer, recognition time and waiting time become large if it is recognized after it is written (batch recognition). Thus, incremental methods have been proposed with recognition triggered by every stroke but the recognition rates are damaged and more CPU time is incurred. We propose semi-incremental recognition and employ a local processing strategy by focusing on a recent sequence of strokes defined as ”scope” rather than every new stroke. For the latest scope, we build and update a segmentation and recognition candidate lattice and advance the best-path search incrementally. We utilize the result of the best-path search in the previous scope to exclude unnecessary segmentation candidates. This reduces the number of candidate character recognition with the result of reduced processing time. We also reuse the segmentation and recognition candidate lattice in the previous scope for the latest scope. Moreover, triggering recognition processes every several strokes saves CPU time. Experiments made on TUAT-Kondate database show the effectiveness of the proposed semi-incremental recognition method not only in reduced processing time and waiting time, but also in recognition accuracy.
Cuong-Tuan NGUYEN
Tokyo University of Agriculture and Technology
Bilan ZHU
Tokyo University of Agriculture and Technology
Masaki NAKAGAWA
Tokyo University of Agriculture and Technology
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
Cuong-Tuan NGUYEN, Bilan ZHU, Masaki NAKAGAWA, "Semi-Incremental Recognition of On-Line Handwritten Japanese Text" in IEICE TRANSACTIONS on Information,
vol. E99-D, no. 10, pp. 2619-2628, October 2016, doi: 10.1587/transinf.2016EDP7051.
Abstract: This paper presents a semi-incremental recognition method for on-line handwritten Japanese text and its evaluation. As text becomes longer, recognition time and waiting time become large if it is recognized after it is written (batch recognition). Thus, incremental methods have been proposed with recognition triggered by every stroke but the recognition rates are damaged and more CPU time is incurred. We propose semi-incremental recognition and employ a local processing strategy by focusing on a recent sequence of strokes defined as ”scope” rather than every new stroke. For the latest scope, we build and update a segmentation and recognition candidate lattice and advance the best-path search incrementally. We utilize the result of the best-path search in the previous scope to exclude unnecessary segmentation candidates. This reduces the number of candidate character recognition with the result of reduced processing time. We also reuse the segmentation and recognition candidate lattice in the previous scope for the latest scope. Moreover, triggering recognition processes every several strokes saves CPU time. Experiments made on TUAT-Kondate database show the effectiveness of the proposed semi-incremental recognition method not only in reduced processing time and waiting time, but also in recognition accuracy.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2016EDP7051/_p
Copy
@ARTICLE{e99-d_10_2619,
author={Cuong-Tuan NGUYEN, Bilan ZHU, Masaki NAKAGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Semi-Incremental Recognition of On-Line Handwritten Japanese Text},
year={2016},
volume={E99-D},
number={10},
pages={2619-2628},
abstract={This paper presents a semi-incremental recognition method for on-line handwritten Japanese text and its evaluation. As text becomes longer, recognition time and waiting time become large if it is recognized after it is written (batch recognition). Thus, incremental methods have been proposed with recognition triggered by every stroke but the recognition rates are damaged and more CPU time is incurred. We propose semi-incremental recognition and employ a local processing strategy by focusing on a recent sequence of strokes defined as ”scope” rather than every new stroke. For the latest scope, we build and update a segmentation and recognition candidate lattice and advance the best-path search incrementally. We utilize the result of the best-path search in the previous scope to exclude unnecessary segmentation candidates. This reduces the number of candidate character recognition with the result of reduced processing time. We also reuse the segmentation and recognition candidate lattice in the previous scope for the latest scope. Moreover, triggering recognition processes every several strokes saves CPU time. Experiments made on TUAT-Kondate database show the effectiveness of the proposed semi-incremental recognition method not only in reduced processing time and waiting time, but also in recognition accuracy.},
keywords={},
doi={10.1587/transinf.2016EDP7051},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Semi-Incremental Recognition of On-Line Handwritten Japanese Text
T2 - IEICE TRANSACTIONS on Information
SP - 2619
EP - 2628
AU - Cuong-Tuan NGUYEN
AU - Bilan ZHU
AU - Masaki NAKAGAWA
PY - 2016
DO - 10.1587/transinf.2016EDP7051
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E99-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2016
AB - This paper presents a semi-incremental recognition method for on-line handwritten Japanese text and its evaluation. As text becomes longer, recognition time and waiting time become large if it is recognized after it is written (batch recognition). Thus, incremental methods have been proposed with recognition triggered by every stroke but the recognition rates are damaged and more CPU time is incurred. We propose semi-incremental recognition and employ a local processing strategy by focusing on a recent sequence of strokes defined as ”scope” rather than every new stroke. For the latest scope, we build and update a segmentation and recognition candidate lattice and advance the best-path search incrementally. We utilize the result of the best-path search in the previous scope to exclude unnecessary segmentation candidates. This reduces the number of candidate character recognition with the result of reduced processing time. We also reuse the segmentation and recognition candidate lattice in the previous scope for the latest scope. Moreover, triggering recognition processes every several strokes saves CPU time. Experiments made on TUAT-Kondate database show the effectiveness of the proposed semi-incremental recognition method not only in reduced processing time and waiting time, but also in recognition accuracy.
ER -