This paper proposes a "structuring search space" (SSS) method aimed to accelerate recognition of large character sets. We divide the feature space of character categories into smaller clusters and derive the centroid of each cluster as a pivot. Given an input pattern, it is compared with all the pivots and only a limited number of clusters whose pivots have higher similarity (or smaller distance) to the input pattern are searched in, thus accelerating the recognition speed. This is based on the assumption that the search space is a distance space. We also consider two ways of candidate selection and finally combine them the method has been applied to a practical off-line Japanese character recognizer with the result that the coarse classification time is reduced to 56% and the whole recognition time is reduced to 52% while keeping its recognition rate as the original.
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
Yiping YANG, Bilan ZHU, Masaki NAKAGAWA, "Structuring Search Space for Accelerating Large Set Character Recognition" in IEICE TRANSACTIONS on Information,
vol. E88-D, no. 8, pp. 1799-1806, August 2005, doi: 10.1093/ietisy/e88-d.8.1799.
Abstract: This paper proposes a "structuring search space" (SSS) method aimed to accelerate recognition of large character sets. We divide the feature space of character categories into smaller clusters and derive the centroid of each cluster as a pivot. Given an input pattern, it is compared with all the pivots and only a limited number of clusters whose pivots have higher similarity (or smaller distance) to the input pattern are searched in, thus accelerating the recognition speed. This is based on the assumption that the search space is a distance space. We also consider two ways of candidate selection and finally combine them the method has been applied to a practical off-line Japanese character recognizer with the result that the coarse classification time is reduced to 56% and the whole recognition time is reduced to 52% while keeping its recognition rate as the original.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e88-d.8.1799/_p
Copy
@ARTICLE{e88-d_8_1799,
author={Yiping YANG, Bilan ZHU, Masaki NAKAGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Structuring Search Space for Accelerating Large Set Character Recognition},
year={2005},
volume={E88-D},
number={8},
pages={1799-1806},
abstract={This paper proposes a "structuring search space" (SSS) method aimed to accelerate recognition of large character sets. We divide the feature space of character categories into smaller clusters and derive the centroid of each cluster as a pivot. Given an input pattern, it is compared with all the pivots and only a limited number of clusters whose pivots have higher similarity (or smaller distance) to the input pattern are searched in, thus accelerating the recognition speed. This is based on the assumption that the search space is a distance space. We also consider two ways of candidate selection and finally combine them the method has been applied to a practical off-line Japanese character recognizer with the result that the coarse classification time is reduced to 56% and the whole recognition time is reduced to 52% while keeping its recognition rate as the original.},
keywords={},
doi={10.1093/ietisy/e88-d.8.1799},
ISSN={},
month={August},}
Copy
TY - JOUR
TI - Structuring Search Space for Accelerating Large Set Character Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1799
EP - 1806
AU - Yiping YANG
AU - Bilan ZHU
AU - Masaki NAKAGAWA
PY - 2005
DO - 10.1093/ietisy/e88-d.8.1799
JO - IEICE TRANSACTIONS on Information
SN -
VL - E88-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2005
AB - This paper proposes a "structuring search space" (SSS) method aimed to accelerate recognition of large character sets. We divide the feature space of character categories into smaller clusters and derive the centroid of each cluster as a pivot. Given an input pattern, it is compared with all the pivots and only a limited number of clusters whose pivots have higher similarity (or smaller distance) to the input pattern are searched in, thus accelerating the recognition speed. This is based on the assumption that the search space is a distance space. We also consider two ways of candidate selection and finally combine them the method has been applied to a practical off-line Japanese character recognizer with the result that the coarse classification time is reduced to 56% and the whole recognition time is reduced to 52% while keeping its recognition rate as the original.
ER -