Journal of architectural history (건축역사연구)

Korean Association of Architectural History (한국건축역사학회)
권호 표지
DOI QR코드

DOI QR Code

Denoising Traditional Architectural Drawings with Image Generation and Supervised Learning

이미지 생성 및 지도학습을 통한 전통 건축 도면 노이즈 제거

  • 최낙관 (울산과학기술원 전자공학과) ;
  • 이용식 (한국전자통신연구원) ;
  • 이승재 (한국전자통신연구원) ;
  • 양승준 (울산과학기술원 전자공학과)
  • Received : 2021.12.06
  • Accepted : 2022.02.15
  • Published : 2022.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

Traditional wooden buildings deform over time and are vulnerable to fire or earthquakes. Therefore, traditional wooden buildings require continuous management and repair, and securing architectural drawings is essential for repair and restoration. Unlike modernized CAD drawings, traditional wooden building drawings scan and store hand-drawn drawings, and in this process, many noise is included due to damage to the drawing itself. These drawings are digitized, but their utilization is poor due to noise. Difficulties in systematic management of traditional wooden buildings are increasing. Noise removal by existing algorithms has limited drawings that can be applied according to noise characteristics and the performance is not uniform. This study presents deep artificial neural network based noised reduction for architectural drawings. Front/side elevation drawings, floor plans, detail drawings of Korean wooden treasure buildings were considered. First, the noise properties of the architectural drawings were learned with both a cycle generative model and heuristic image fusion methods. Consequently, a noise reduction network was trained through supervised learning using training sets prepared using the noise models. The proposed method provided effective removal of noise without deteriorating fine lines in the architectural drawings and it showed good performance for various noise types.

Keywords

Acknowledgement

This research was supported by 2022 Cultural Heritage Smart Preservation & Utilization R&D Program of Cultural Heritage Administration, National Research Institute of Cultural Heritage. (Project Name: Development of AI-based CAD conversion technology for traditional architecture drawing images, Project Number: 2022A02P03-001, Contribution Rate: 100%)

References

  1. 안대환, 목조 건축문화재 실측조사보고서에서 3D 스캔 데이터 활용의 기술 (記述) 내용에 관한 연구. 대한건축학회 논문집-계획계, 2015, 31.1: 65-74.
  2. 백민호.이해평, 전통사찰문화재의 방재대책에 관한연구. 한국화재소방학회 논문지, 2006, 20.2: 64-71.
  3. KRIZHEVSKY, Alex.SUTSKEVER, Ilya.HINTON, Geoffrey E, Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 2012, 25: 1097-1105.
  4. 이가윤, et al. 국내외 건축 문화재 지진 피해 사례 및 대응 현황. 한국공간구조학회지, 2020, 20.1: 4-11.
  5. 이영병, 화제사례-숭례문 화재사례 및 문화재 안전관리 대책. 방재와보험, 2008, 48-54.
  6. RONNEBERGER, Olaf.FISCHER, Philipp.BROX, Thomas, U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015. p. 234-241.
  7. SABA, Tanzila, et al. Evaluation of current documents image denoising techniques: a comparative study. Applied Artificial Intelligence, 2014, 28.9: 879-887. https://doi.org/10.1080/08839514.2014.954344
  8. SHI, Zhenghao, et al. A Chinese character structure preserved denoising method for Chinese tablet calligraphy document images based on KSVD dictionary learning. Multimedia Tools and Applications, 2017, 76.13: 14921-14936. https://doi.org/10.1007/s11042-016-4284-3
  9. 신병욱, 목조건축문화재에 있어서 변위 및 손상 유형에 관한 연구. 한국농촌건축학회논문집, 2019, 21.3: 25-32. https://doi.org/10.14577/kirua.2019.21.3.25
  10. ZHANG, Yudong, A fast document image denoising method based on packed binary format and source word accumulation. 2011.
  11. ZHU, Jun-Yan, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision. 2017. p. 2223-2232.
  12. 국립문화재연구소, (2019) 국가지정 건조물문화재 국보.보물 정기조사:서울, 국립문화재연구소, 2020, 16-21
  13. EGIAZARIAN, Vage, et al. Deep vectorization of technical drawings. In: European Conference on Computer Vision. Springer, Cham, 2020. p. 582-598.