지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2023.12
- 수록면
- 973 - 979 (7page)
- DOI
- 10.5302/J.ICROS.2023.23.0146
이용수
초록· 키워드
오류제보하기
Despite significant advancements in scene text recognition, current models face substantial challenges, particularly when confronted with irregular text images featuring complex backgrounds, curved text, diverse fonts, and distortions. While convolutional neural network (CNN)-based text recognition networks have demonstrated commendable performance, they grapple with the aforementioned challenges. Recently, transformer-based feature extractors have exhibited advantages in global feature extraction from images, especially in the context of irregular text images. By employing self-attention, these transformers establish information connections between different parts of the image, thereby mitigating the impact of uneven character distribution. This study proposes multi-encoder scene text recognition (MESTR), a hybrid approach that combines a CNN-based and a transformer-based feature extractor. MESTR excels in simultaneously extracting local and global features from text images, ensuring the integration of both types of features to enhance performance. During training, we employed a guiding connectionist temporal classification (CTC) decoder [6] as a compensatory training strategy for the attentional decoder. Our experiments showed the efficacy of MESTR across seven benchmarks, demonstrating robust performance. In addition, ablation experiments are presented to validate the effectiveness of the proposed algorithm for scene text recognition.
목차
Abstract
Ⅰ. 서론
Ⅱ. 관련 연구
Ⅲ. 제안 방법
Ⅳ. 실험 결과
Ⅴ. 결론
REFERENCES
참고문헌 (38)
참고문헌 신청
X. X. Chen, L. W. Jin, Y. Z. Zhu, C. J. Luo, and T. W. Wang, “Text Recognition in the wild: A Survey," arXiv:2005.03492v3, 2020.
B. Shi; M. Yang, X. Wang, P. Lyu, C. Yao, and X. Bai, “Aster: An attentional scene text recognizer with flexible rectification," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 9, pp. 2035-2048, 2018.
B. Shi, X. Wang, P. Lyu, C. Yao, and X. Bai, “Robust scene text recognition with automatic rectification," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4168–4176, 2016
F. Zhan and S. Lu. “ESIR: End-to-end scene text recognition via iterative image rectification," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2059–2068, 2019.
X. Qi, Y. Chen, R. Xiao, C.-G. Li, Q. Zou, and S. Cui, “A novel joint character categorization and localization approach for character-level scene text recognition," 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), pp
B. Shi; M. Yang, X. Wang, P. Lyu, C. Yao, and X. Bai, “Aster: An attentional scene text recognizer with flexible rectification," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 41, no. 9, pp. 2035-2048, 2018.
B. Shi, X. Wang, P. Lyu, C. Yao, and X. Bai, “Robust scene text recognition with automatic rectification," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4168–4176, 2016
F. Zhan and S. Lu. “ESIR: End-to-end scene text recognition via iterative image rectification," Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2059–2068, 2019.
X. Qi, Y. Chen, R. Xiao, C.-G. Li, Q. Zou, and S. Cui, “A novel joint character categorization and localization approach for character-level scene text recognition," 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), pp
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
Scene Text Recognition with Multi-Encoders
제어로봇시스템학회 국제학술대회 논문집
2022 .11
-
다중 패치를 이용한 트랜스포머 기반 장면 텍스트 인식
제어로봇시스템학회 논문지
2022 .10
-
Scene Text Recognition with Multi-decoders
제어로봇시스템학회 국제학술대회 논문집
2021 .10
-
ATSR: 단어 인식기에 필요한 것은 트랜스포머
대한전자공학회 학술대회
2020 .08
-
장면 이미지 속 한글 문자 인식을 위한 글자 단위 일관성 정규화 기반의 준지도학습 모델
대한산업공학회 추계학술대회 논문집
2022 .11
-
장면 이미지 속 한글 문자 인식을 위한 글자 단위 일관성 정규화 기반의 준지도학습 모델
대한산업공학회지
2023 .06
-
회전 심볼-텍스트 통합인식모델을 활용한 이미지 형식 P&ID 인식기법
한국CDE학회 논문집
2025 .03
-
심층 신경망을 이용한 장면 텍스트 추출 및 인식
제어로봇시스템학회 국내학술대회 논문집
2020 .07
-
장면 이미지 속 한글 문자를 종단 간 검출 및 인식 가능한 딥러닝 네트워크 모델
대한산업공학회지
2022 .08
-
Information mining from a Text Image using Smartphone
한국정보과학회 학술발표논문집
2019 .06
-
A Convolutional Neural Network Approach for Classification of Text based on the Texts Collected from Web
INTERNATIONAL CONFERENCE ON FUTURE INFORMATION & COMMUNICATION ENGINEERING
2018 .06
-
다국어 장면 문자 탐지를 위한 다중 수준 특징 결합 네트워크
대한전자공학회 학술대회
2022 .11
-
Real-time Deep Learning-based Scene Recognition Model For Metaverse Applications
한국통신학회 학술대회논문집
2022 .02
-
Deep-Learning Approach for Text Detection Using Fully Convolutional Networks
International JOURNAL OF CONTENTS
2018 .03
-
Text Detection in Scene Images Based on Interest Points
JIPS(Journal of Information Processing Systems)
2015 .01
-
Text Recognition을 이용한 효율적인 객체 태깅 방법에 관한 연구
대한전자공학회 학술대회
2019 .11
-
Convolutional Neural Network Based Image Processing System
Journal of information and communication convergence engineering
2018 .09
-
Development and Evaluation of Text-to-Scene Model for Korean Language Writing Education as a Foreign Language
한국컴퓨터게임학회논문지
2018 .01
-
A Hybrid Image Search System: Enhancing Retrieval Performance Using CLIP Embeddings and Scene Text Recognition
한국정보과학회 학술발표논문집
2024 .12
-
다중 언어로 학습된 이미지 기반 문자인식 모델의 성능 분석
대한전자공학회 학술대회
2023 .06
이 논문의 저자 정보
이 논문과 함께 이용한 논문
최근 본 자료
댓글(0)
0