[논문]대안적 통째학습 기반 저품질 레거시 콘텐츠에서의 문자 인식 알고리즘

이성진; 윤준석; 박선후; 유석봉

doi:10.6109/jkiice.2021.25.11.1486

대안적 통째학습 기반 저품질 레거시 콘텐츠에서의 문자 인식 알고리즘
Character Recognition Algorithm in Low-Quality Legacy Contents Based on Alternative End-to-End Learning 원문보기

한국정보통신학회논문지 = Journal of the Korea Institute of Information and Communication Engineering, v.25 no.11, 2021년, pp.1486 - 1494

이성진 (Department of AI Convergence, Chonnam National University) , 윤준석 (Department of AI Convergence, Chonnam National University) , 박선후 (Department of SW Engineering, Chonnam National University) , 유석봉 (Department of AI Convergence, Chonnam National University)

초록
AI-Helper

문자 인식은 스마트 주차, text to speech 등 최근 다양한 플랫폼에서 필요로 하는 기술로써, 기존의 방법과 달리 새로운 시도를 통하여 그 성능을 향상시키려는 연구들이 진행되고 있다. 그러나 문자 인식에 사용되는 이미지의 품질이 낮을 경우, 문자 인식기 학습용 이미지와 테스트 이미지간에 해상도 차이가 발생하여 정확도가 떨어지는 문제가 발생된다. 이를 해결하기 위해 본 논문은 문자 인식 모델 성능이 다양한 품질 데이터에 대하여 강인하도록 이미지 초해상도 및 문자 인식을 결합한 통째학습 신경망을 설계하고, 대안적 통째학습 알고리즘을 구현하여 통째 신경망 학습을 수행하였다. 다양한 문자 이미지 중 차량 번호판 이미지를 이용하여 대안적 통째학습 및 인식 성능 테스트를 진행하였고, 이를 통해 제안하는 알고리즘의 효과를 검증하였다.

Abstract ▼ AI-Helper

Character recognition is a technology required in various platforms, such as smart parking and text to speech, and many studies are being conducted to improve its performance through new attempts. However, with low-quality image used for character recognition, a difference in resolution of the training image and test image for character recognition occurs, resulting in poor accuracy. To solve this problem, this paper designed an end-to-end learning neural network that combines image super-resolution and character recognition so that the character recognition model performance is robust against various quality data, and implemented an alternative whole learning algorithm to learn the whole neural network. An alternative end-to-end learning and recognition performance test was conducted using the license plate image among various text images, and the effectiveness of the proposed algorithm was verified with the performance test.

주제어

표/그림 (7)

그림 Fig. 2 Flowchart of integrated network of SR network and character recognition network for end-to-end learning.
그림 Fig. 1 The flowchart of SR framework.
그림 Fig. 3 Flowchart of alternative end-to-end learning. (a) SR training with freezing character recognition network, (b) Character recognition training with freezing SR network.
그림 Fig. 4 (a) Diagram of patch extraction based SR, (b) Diagram of global image feature extraction based SR.
표 Table. 1 Comparision of PSNR(dB) and mAP(%).
그림 Fig. 5 SR(x4) and character recognition results of plate images on (a) bicubic images, (b) SR images, (c) end-toend learning results, (d) HR images. Two characters were masked due to privacy policy.
표 Table. 2 Comparision of mAP(%).

참고문헌 (18)

Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, "Image quality assessment: from error visibility to structural similarity," IEEE Transactions on Image Processing, vol. 13, no. 4, pp. 600-612, 2004.

상세보기
W. Xing and K. Egiazarian, "End-to-end learning for joint image demosaicing, denoising and super-resolution," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3507-3516, 2021.
Y. Wei, S. Gu, Y. Li, R. Timofte, L. Jin, and H. Song, "Unsupervised real-world image super resolution via domain-distance aware training" in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 13385-13394, 2021.
L. Wang, X. Dong, Y, Wang. X, Ying, Z. Lin, W. An, and Y. Guo, "Exploring sparsity in image super-resolution for efficient inference," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4917-4926, 2021.
Y. Jo, S. W. Oh, P. Vajda, and S. J. Kim, "Tackling the ill-posedness of super-resolution through adaptive target generation," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16236-16245, 2021.
A. Bochkovskiy, C. Y. Wang, and H. Y. M. Liao, "YOLOv4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.
J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.
Darknet: Open source neural networks in C [Internet]. Available: https://pjreddie.com/darknet/.
Ultralytics. YOLOv5 [Internet]. Available: https://github.com/ultralytics/yolov5.
G. Huang, Z. Liu, L. Maaten, and K. Q. Weinberger, "Densely connected convolutional networks," in Proceeding of the 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, HI, USA, pp. 2261-2269, 2017.
C. Y. Wang, H. Y. M. Liao, Y. H. Wu, P. Y. Chen, J. W. Hsieh, and I. H. Yeh, "CSPNet: A new backbone that can enhance learning capability of CNN," in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 390-391, 2020.
S. Qiao, L. C. Chen, and A. Yuille, "DetectoRS: Detecting objects with recursive feature pyramid and switchable atrous convolution," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10213-10224, Jun. 2021.
J. G. Seo and H. Y. Park, "Object Recognition in very low resolution images using deep collaborative learning," in IEEE Access, vol. 7, pp. 134071-134082, 2019.

상세보기
J. Chen, B. Li, and X. Xue, "Scene text telescope: Text-focused scene image super-resolution," in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 12026-12035, Jun. 2021.
S. J. Lee, T. J. Kim, C. H. Lee, and S. B. Yoo, "Image super-resolution for improving object recognition accuracy," Journal of the Korea Institute of Information and Communication Engineering, vol. 25, no. 6, pp. 774-784, Jun. 2021.

원문보기 상세보기
T. Y. Song, Y. H. Lee, M. J. Kim, B. H. Ku, and H. S. Ko, "Fusion methods of license plate detection and super resolution for improving license plate recognition," Journal of The Korea Society of Computer and Information, vol. 16, no. 4, pp. 53-60, Apr. 2011.

원문보기 상세보기
J. Jiao, W. S. Zheng, A. Wu, X. Zhu, and S. Gong, "Deep low-resolution person re-identification," in Proceeding of the 32nd AAAI Conference on Artificial Intelligence, 2018.
M. Haris, G. Shakhnarovich, and N. Ukita, "Deep back-projection networks for super-resolution," in Proceeding of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1664-1673, Mar. 2018.

내보내기 구분	파일저장 인쇄 메일전송
구성항목	기본정보 상세정보 관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관 관리번호, 논문명, 대등논문명, 저자 , 저널/프로시딩명, 발행기관, 발행년, 발행언어, 권, 호, 시작페이지, 끝페이지, ISBN, ISSN, 주제분야, 키워드, 초록(한글), 초록(영문), 저자(소속기관)
저장형식	Text(ASCII format) Excel format RefWorks Direct Export RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley
메일정보	받는사람 (필수) @ 보내는사람 (선택) @ 제목 내용 KISTI 검색결과 이메일 서비스
안내	총 건의 자료가 검색되었습니다. 다운받으실 자료의 인덱스를 입력하세요. (1-10,000) 검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다. 데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요) 다운로드 파일은 UTF-8 형태로 저장됩니다. 파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오. ~ Text(ASCII format) Excel format

연합인증