한국문헌정보학회지 (Journal of the Korean Society for Library and Information Science)

한국문헌정보학회 (Korean Society For Library And Information Science)
권호 표지
DOI QR코드

DOI QR Code

랜드마크 이미지 AI 학습용 데이터 구축을 위한 메타데이터 표준 설계 방안 연구

A Study on Designing Metadata Standard for Building AI Training Dataset of Landmark Images

  • 김진묵 (강남대학교 산업데이터사이언스학부)
  • 투고 : 2020.05.22
  • 심사 : 2020.05.25
  • 발행 : 2020.05.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 연구의 목적은 랜드마크 이미지의 AI 학습용 데이터 구축을 위한 메타데이터 표준 설계 방안을 제시하기 위함이다. 이를 위해, 이미지 검색시스템의 종류와 각각의 색인 방식에 관한 최신 기술 현황을 포괄적으로 조사하여 분석하고, AI 머신러닝을 적용한 랜드마크 인식에 필수적인 학습용 공개 데이터셋과 이미지 객체 인식에 관한 기계학습 도구를 조사하였다. 이를 통해, 랜드마크 이미지 AI 학습용 데이터에 최적화된 메타데이터 요소를 선정하고 각각의 요소에 대한 입력 데이터를 정의하였다. 결론 및 제언에서는 랜드마크 인식을 활용한 추천시스템을 포함한 응용서비스 개발 방안을 논의하였다.

The purpose of the study is to design and propose metadata standard for building AI training dataset of landmark images. In order to achieve the purpose, we first examined and analyzed the state of art of the types of image retrieval systems and their indexing methods, comprehensively. We then investigated open training dataset and machine learning tools for image object recognition. Sequentially, we selected metadata elements optimized for the AI training dataset of landmark images and defined the input data for each element. We then concluded the study with implications and suggestions for the development of application services using the results of the study.

키워드

참고문헌

  1. National Library of Korea, Korean Bibliography, Dublin Core Homepage. [online] [cited 2020. 5. 10.]
  2. 권은영, 나연묵. 2004. 의미기반 이미지 검색을 위한 통합 이미지 메타데이타의 설계 및 구현. 한국정보과학회 학술발표논문집, 31(2): 145-147.
  3. Kim, S., and Yi, K. 2004. "A study on the retrieval effectiveness based on image query types." Journal of the Korean Society for Library and Information Science, 47(3): 321-342. https://doi.org/10.4275/KSLIS.2013.47.3.321
  4. Kim, J. 2018. "A study on the development of collaborative filtering systems and its application." Journal of Social Science Research, 29(2): 197-209.
  5. Naver Korean Dictionary. [online] [cited 2020. 5. 10.]
  6. Naver Cloud Platform Homepage. [online] [cited 2020. 5. 10.]
  7. Mo, Y. and Lee, C. 2009. "A study on increasing the efficiency of image search using image attribute in the area of content-based image retrieval." Journal of the Korea Society for Simulation, 18(2): 39-48.
  8. Park, Y., Song, K., Whang, J. and Chang, B. 2015. "A system for personalized tour recommendation based on ontology." Journal of the Korea Contents Association, 15(9): 1-10. https://doi.org/10.5392/JKCA.2015.15.09.001
  9. Byeon, J. et al. 2006. "The classification of cities based on urban images." Journal of Korea Planning Association, 41(3): 7-20.
  10. Lee, Y. and Nang, J. 2018. "Building training image dataset and experiments with convolutional neural network for Seoul landmark recognition." Proceedings of Korea Information Science Society, 845-847.
  11. Lee, H. et. al. 2019. "Fashion image searching website based on deep learning image classification." Journal of Practical Engineering Education, 11(2): 175-180. https://doi.org/10.14702/JPEE.2019.175
  12. Lim, Chae-Suk. 2016. "A study on the landmark for regional revitalization." Journal of the Korea Academica-Industrial Cooperation Society, 17(3): 560-570.
  13. Chung, Kyung-Yong. 2008. "Pernalized item recommendation using image-based filtering." Journal of the Korea Contents Association, 8(3): 1-7. https://doi.org/10.5392/JKCA.2008.8.3.001
  14. Chung, EunKyung. 2014. "A systematic review on concept-based image retrieval research." Journal of the Korean Biblia Society for Library and Information Science, 25(4): 313-332. https://doi.org/10.14699/kbiblia.2014.25.4.313
  15. Choi, M. 2017. "Complex color model for efficient representation of color-shape in contextbased image retrieval." Journal of Digital Convergence, 15(4): 267-273. https://doi.org/10.14400/JDC.2017.15.4.267
  16. kakao Vision API Homepage. [online] [cited 2020. 5. 10.]
  17. Hong, S. and Nah, Y. 2000. "A design and implementation of intelligent image retrieval system using hybrid image metadata." Journal of Korea Multimedia Society, 3(3): 209-223.
  18. Carson, C., Thomas, M., Belongie, S., Hellerstein, J. M. and Malik, J. 1999. Blobworld: A system for region-based image indexing and retrieval. Technical Report: UCB/CSD-99-1041, University of California, Berleley, 1-12. [online] [cited 2020. 5. 10.]
  19. Data et al. 2008. "Image retrieval: Ideas, influences, and trends of the new age." ACM Computing Surveys, 40(2): 1-60. https://doi.org/10.1145/1348246.1348248
  20. Firebase homepage [online] [cited 2020. 5. 10.]
  21. Karlsen, R., Elahi, N. and Andersen, A. 2018. Personalized recommendation of socially relevant images. Proceedings of 8th Conference on Web Intelligence, Mining and Semantics, pp.1-4. [online] [cited 2020. 5. 10.]
  22. Kim, Jaeyoon. 2019. Regional attention based deep feature for image retrieval. Master's Theses, KAIST.
  23. Lew, M. S. et al. 2006. "Content-based multimedia information retrieval: State of the art and challenges." ACM Transactions on Multimedia Computing, Communications, and Applications, 2(1): 1-19. https://doi.org/10.1145/1126004.1126005
  24. Melo, E. V. 2018. "Improving collaborative filtering-based image recommendation through use of eye gaze tracking." Information, 9(11): 262-274. https://doi.org/10.3390/info9110262
  25. Noh, A., Araujo, A., Sim, J., Weyand, T. and Han, B. 2017. Large-scale image retrieval with attentive deep local features. Proceedings of the IEEE International Conference on Computer Vision, 3456-3465.
  26. Smith, J. R. and Chang, S.-F, 1997. "Visually searching the Web for Content." IEEE Multimedia Magazine, 4(3): 12-20. https://doi.org/10.1109/93.621578
  27. Srivastava, G. and Srivastava, R. 2020. "Design, analysis and implementation of efficient framework for immage annotation." ACM Transactions on Multimedia Computing, Communications, and Applications, Accepted on February, 2020.