The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
이 논문은 일본 역사 문서에서 변칙적으로 변형된 가나 시퀀스에 대한 인식을 제시합니다. IEICE PRMU 2017. 콘테스트는 인식되는 문자 수에 따라 1가지 레벨로 나누어졌습니다. 레벨 2: 단일 문자, 레벨 3: 세로로 쓰여진 세 개의 가나 문자 시퀀스, 레벨 2: 세 개 이상의 문자로 구성된 무제한 문자 세트 여러 줄에 더 많은 문자가 포함될 수 있습니다. 본 논문은 콘테스트에서 우승한 레벨 3와 레벨 2의 방법에 초점을 맞췄습니다. 우리는 기본적으로 분할 없는 접근 방식을 따르고 특징 추출을 위한 CNN(Convolutional Neural Network), 프레임 예측을 위한 BLSTM(BiDirectional Long Short-Term Memory), 텍스트 인식을 위한 CTC(Connectionist Temporal Classification)의 계층 구조를 사용합니다. DCRN(Deep Convolutional Recurrent Network)이라고 합니다. 사전 훈련된 CNN 접근 방식과 엔드 투 엔드 접근 방식을 레벨 3에 대해 보다 세부적인 변형과 비교합니다. 그런 다음 레벨 2에 DCRN을 적용하기 전에 수직 텍스트 라인 분할 및 다중 라인 연결 방법을 제안합니다. 레벨 3을 위한 차원적 BLSTM(89.10DBLSTM) 기반 방법. 교차 검증을 통해 최상의 방법에 대한 평가를 제시합니다. 우리는 세 개의 가나 문자 시퀀스 인식에 대해 87.70%의 정확도를 달성했으며, 언어적 맥락을 사용하지 않고 무제한 가나 인식에 대해 2%의 정확도를 달성했습니다. 이러한 결과는 제안된 모델이 레벨 3와 레벨 XNUMX 작업에 대한 성능을 입증한다.
Nam Tuan LY
Tokyo University of Agriculture and Technology
Kha Cong NGUYEN
Tokyo University of Agriculture and Technology
Cuong Tuan NGUYEN
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.
부
Nam Tuan LY, Kha Cong NGUYEN, Cuong Tuan NGUYEN, Masaki NAKAGAWA, "Recognition of Anomalously Deformed Kana Sequences in Japanese Historical Documents" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 8, pp. 1554-1564, August 2019, doi: 10.1587/transinf.2018EDP7361.
Abstract: This paper presents recognition of anomalously deformed Kana sequences in Japanese historical documents, for which a contest was held by IEICE PRMU 2017. The contest was divided into three levels in accordance with the number of characters to be recognized: level 1: single characters, level 2: sequences of three vertically written Kana characters, and level 3: unrestricted sets of characters composed of three or more characters possibly in multiple lines. This paper focuses on the methods for levels 2 and 3 that won the contest. We basically follow the segmentation-free approach and employ the hierarchy of a Convolutional Neural Network (CNN) for feature extraction, Bidirectional Long Short-Term Memory (BLSTM) for frame prediction, and Connectionist Temporal Classification (CTC) for text recognition, which is named a Deep Convolutional Recurrent Network (DCRN). We compare the pretrained CNN approach and the end-to-end approach with more detailed variations for level 2. Then, we propose a method of vertical text line segmentation and multiple line concatenation before applying DCRN for level 3. We also examine a two-dimensional BLSTM (2DBLSTM) based method for level 3. We present the evaluation of the best methods by cross validation. We achieved an accuracy of 89.10% for the three-Kana-character sequence recognition and an accuracy of 87.70% for the unrestricted Kana recognition without employing linguistic context. These results prove the performances of the proposed models on the level 2 and 3 tasks.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2018EDP7361/_p
부
@ARTICLE{e102-d_8_1554,
author={Nam Tuan LY, Kha Cong NGUYEN, Cuong Tuan NGUYEN, Masaki NAKAGAWA, },
journal={IEICE TRANSACTIONS on Information},
title={Recognition of Anomalously Deformed Kana Sequences in Japanese Historical Documents},
year={2019},
volume={E102-D},
number={8},
pages={1554-1564},
abstract={This paper presents recognition of anomalously deformed Kana sequences in Japanese historical documents, for which a contest was held by IEICE PRMU 2017. The contest was divided into three levels in accordance with the number of characters to be recognized: level 1: single characters, level 2: sequences of three vertically written Kana characters, and level 3: unrestricted sets of characters composed of three or more characters possibly in multiple lines. This paper focuses on the methods for levels 2 and 3 that won the contest. We basically follow the segmentation-free approach and employ the hierarchy of a Convolutional Neural Network (CNN) for feature extraction, Bidirectional Long Short-Term Memory (BLSTM) for frame prediction, and Connectionist Temporal Classification (CTC) for text recognition, which is named a Deep Convolutional Recurrent Network (DCRN). We compare the pretrained CNN approach and the end-to-end approach with more detailed variations for level 2. Then, we propose a method of vertical text line segmentation and multiple line concatenation before applying DCRN for level 3. We also examine a two-dimensional BLSTM (2DBLSTM) based method for level 3. We present the evaluation of the best methods by cross validation. We achieved an accuracy of 89.10% for the three-Kana-character sequence recognition and an accuracy of 87.70% for the unrestricted Kana recognition without employing linguistic context. These results prove the performances of the proposed models on the level 2 and 3 tasks.},
keywords={},
doi={10.1587/transinf.2018EDP7361},
ISSN={1745-1361},
month={August},}
부
TY - JOUR
TI - Recognition of Anomalously Deformed Kana Sequences in Japanese Historical Documents
T2 - IEICE TRANSACTIONS on Information
SP - 1554
EP - 1564
AU - Nam Tuan LY
AU - Kha Cong NGUYEN
AU - Cuong Tuan NGUYEN
AU - Masaki NAKAGAWA
PY - 2019
DO - 10.1587/transinf.2018EDP7361
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 8
JA - IEICE TRANSACTIONS on Information
Y1 - August 2019
AB - This paper presents recognition of anomalously deformed Kana sequences in Japanese historical documents, for which a contest was held by IEICE PRMU 2017. The contest was divided into three levels in accordance with the number of characters to be recognized: level 1: single characters, level 2: sequences of three vertically written Kana characters, and level 3: unrestricted sets of characters composed of three or more characters possibly in multiple lines. This paper focuses on the methods for levels 2 and 3 that won the contest. We basically follow the segmentation-free approach and employ the hierarchy of a Convolutional Neural Network (CNN) for feature extraction, Bidirectional Long Short-Term Memory (BLSTM) for frame prediction, and Connectionist Temporal Classification (CTC) for text recognition, which is named a Deep Convolutional Recurrent Network (DCRN). We compare the pretrained CNN approach and the end-to-end approach with more detailed variations for level 2. Then, we propose a method of vertical text line segmentation and multiple line concatenation before applying DCRN for level 3. We also examine a two-dimensional BLSTM (2DBLSTM) based method for level 3. We present the evaluation of the best methods by cross validation. We achieved an accuracy of 89.10% for the three-Kana-character sequence recognition and an accuracy of 87.70% for the unrestricted Kana recognition without employing linguistic context. These results prove the performances of the proposed models on the level 2 and 3 tasks.
ER -