Feature representation, as a key component of scene character recognition, has been widely studied and a number of effective methods have been proposed. In this letter, we propose the novel method named coupled spatial learning (CSL) for scene character representation. Different from the existing methods, the proposed CSL method simultaneously discover the spatial context in both the dictionary learning and coding stages. Concretely, we propose to build the spatial dictionary by preserving the corresponding positions of the codewords. Correspondingly, we introduce the spatial coding strategy which utilizes the spatiality regularization to consider the relationship among features in the Euclidean space. Based on the spatial dictionary and spatial coding, the spatial context can be effectively integrated in the visual representations. We verify our method on two widely used databases (ICDAR2003 and Chars74k), and the experimental results demonstrate that our method achieves competitive results compared with the state-of-the-art methods. In addition, we further validate the proposed CSL method on the Caltech-101 database for image classification task, and the experimental results show the good generalization ability of the proposed CSL.
Zhong ZHANG
Tianjin Normal University
Hong WANG
Tianjin Normal University
Shuang LIU
Tianjin Normal University
Liang ZHENG
University of Technology Sydney
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
Zhong ZHANG, Hong WANG, Shuang LIU, Liang ZHENG, "Scene Character Recognition Using Coupled Spatial Learning" in IEICE TRANSACTIONS on Information,
vol. E100-D, no. 7, pp. 1546-1549, July 2017, doi: 10.1587/transinf.2017EDL8068.
Abstract: Feature representation, as a key component of scene character recognition, has been widely studied and a number of effective methods have been proposed. In this letter, we propose the novel method named coupled spatial learning (CSL) for scene character representation. Different from the existing methods, the proposed CSL method simultaneously discover the spatial context in both the dictionary learning and coding stages. Concretely, we propose to build the spatial dictionary by preserving the corresponding positions of the codewords. Correspondingly, we introduce the spatial coding strategy which utilizes the spatiality regularization to consider the relationship among features in the Euclidean space. Based on the spatial dictionary and spatial coding, the spatial context can be effectively integrated in the visual representations. We verify our method on two widely used databases (ICDAR2003 and Chars74k), and the experimental results demonstrate that our method achieves competitive results compared with the state-of-the-art methods. In addition, we further validate the proposed CSL method on the Caltech-101 database for image classification task, and the experimental results show the good generalization ability of the proposed CSL.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2017EDL8068/_p
Copy
@ARTICLE{e100-d_7_1546,
author={Zhong ZHANG, Hong WANG, Shuang LIU, Liang ZHENG, },
journal={IEICE TRANSACTIONS on Information},
title={Scene Character Recognition Using Coupled Spatial Learning},
year={2017},
volume={E100-D},
number={7},
pages={1546-1549},
abstract={Feature representation, as a key component of scene character recognition, has been widely studied and a number of effective methods have been proposed. In this letter, we propose the novel method named coupled spatial learning (CSL) for scene character representation. Different from the existing methods, the proposed CSL method simultaneously discover the spatial context in both the dictionary learning and coding stages. Concretely, we propose to build the spatial dictionary by preserving the corresponding positions of the codewords. Correspondingly, we introduce the spatial coding strategy which utilizes the spatiality regularization to consider the relationship among features in the Euclidean space. Based on the spatial dictionary and spatial coding, the spatial context can be effectively integrated in the visual representations. We verify our method on two widely used databases (ICDAR2003 and Chars74k), and the experimental results demonstrate that our method achieves competitive results compared with the state-of-the-art methods. In addition, we further validate the proposed CSL method on the Caltech-101 database for image classification task, and the experimental results show the good generalization ability of the proposed CSL.},
keywords={},
doi={10.1587/transinf.2017EDL8068},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Scene Character Recognition Using Coupled Spatial Learning
T2 - IEICE TRANSACTIONS on Information
SP - 1546
EP - 1549
AU - Zhong ZHANG
AU - Hong WANG
AU - Shuang LIU
AU - Liang ZHENG
PY - 2017
DO - 10.1587/transinf.2017EDL8068
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E100-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2017
AB - Feature representation, as a key component of scene character recognition, has been widely studied and a number of effective methods have been proposed. In this letter, we propose the novel method named coupled spatial learning (CSL) for scene character representation. Different from the existing methods, the proposed CSL method simultaneously discover the spatial context in both the dictionary learning and coding stages. Concretely, we propose to build the spatial dictionary by preserving the corresponding positions of the codewords. Correspondingly, we introduce the spatial coding strategy which utilizes the spatiality regularization to consider the relationship among features in the Euclidean space. Based on the spatial dictionary and spatial coding, the spatial context can be effectively integrated in the visual representations. We verify our method on two widely used databases (ICDAR2003 and Chars74k), and the experimental results demonstrate that our method achieves competitive results compared with the state-of-the-art methods. In addition, we further validate the proposed CSL method on the Caltech-101 database for image classification task, and the experimental results show the good generalization ability of the proposed CSL.
ER -