Journal of the Korean BIBLIA Society for library and Information Science (한국비블리아학회지)

Korean Biblia Society for Library and Information Science (한국비블리아학회)
권호 표지
DOI QR코드

DOI QR Code

Development of an Image Tagging System Based on Crowdsourcing

크라우드소싱 기반 이미지 태깅 시스템 구축 연구

  • 이혜영 (숙명여자대학교 문헌정보학과) ;
  • 장윤금 (숙명여자대학교 문헌정보학과)
  • Received : 2018.08.21
  • Accepted : 2018.09.07
  • Published : 2018.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

This study aims to improve the access and retrieval of images and to find a way to effectively generate tags as a tool for providing explanation of images. To do this, this study investigated the features of human tagging and machine tagging, and compare and analyze them. Machine tags had the highest general attributes, some specific attributes and visual elements, and few abstract attributes. The general attribute of the human tag was the highest, but the specific attribute was high for the object and scene where the human tag constructor can recognize the name. In addition, sentiments and emotions, as well as subjects of abstract concepts, events, places, time, and relationships are represented by various tags. The tag set generated through this study can be used as basic data for constructing training data set to improve the machine learning algorithm.

본 연구는 이미지에 대한 접근 및 검색을 향상시키고, 이미지에 대한 설명 제공 도구로서의 태그를 효과적으로 생성하기 위한 방안을 모색하는데 목적이 있다. 이를 위해 이미지 태그를 생성하는 두 가지 방법인 휴먼 태깅과 머신 태깅의 특징을 조사하고 휴먼 태그와 머신 태그의 속성을 비교 분석하였다. 머신 태그는 일반적 속성이 가장 높았으며, 특정적 속성과 시각적 요소는 일부 나타났고, 추상적 속성은 거의 나타나지 않았다. 휴먼 태그도 일반적 속성이 가장 높았으나 휴먼 태그 생성자가 명칭을 알 수 있는 객체 및 장면에 대해서는 특정적 속성의 비중이 높았으며, 감정과 정서, 추상적 개념의 주제뿐 아니라 사건, 장소, 시간, 관계 등이 다양한 태그로 표현되었다. 본 연구를 통해 생성된 태그 집합은 머신러닝 알고리즘을 개선하기 위한 트레이닝 데이터세트를 구성하는데 기초 자료로 활용될 수 있을 것이다.

Keywords

References

  1. Kim, Hyun-Hee and Min-Kyung Kim. 2009. "Investigating the End-User Tagging Behavior and its Implications in Flickr." Journal of information management, 40(2): 71-94. https://doi.org/10.1633/JIM.2009.40.2.071
  2. Jang, Hyunwoong and Soosun Cho. 2016. "Automatic Tagging for Social Images using Convolution Neural Networks." Journal of KIISE, 43(1): 47-53. https://doi.org/10.5626/JOK.2016.43.1.47
  3. Chung, EunKyung and SunYoung Chung. 2012. "An Approach Toward Image Access Points Based on Image Needs in Context of Everyday Life." Journal of the Korean society for information management, 29(4): 273-294. https://doi.org/10.3743/KOSIM.2012.29.4.273
  4. Chung, EunKyung 2012. "An Exploratory Investigation on Multimedia Information Needs and Searching Behavior among College Students." Journal of the Korean Society for Library and Information Science, 46(3): 251-270. https://doi.org/10.4275/KSLIS.2012.46.3.251
  5. Armitage, L. H. and P. G. B. Enser. 1997. "Analysis of user need in image archives." Journal of Information Science, 23(4): 287-299. https://doi.org/10.1177/016555159702300403
  6. Bar-Ilan, J., M. Zhitomirsky-Geffet, Y. Miller, and S. Shoham. 2010. "The Effects of Background Information and Social Interaction on Image Tagging." Journal of the American Society for Information Science and Technology, 61(5): 940-951. https://doi.org/10.1002/asi.21306
  7. Beaudoin, J. 2007. "Folksonomies: Flickr image tagging: Patterns made visible." Bulletin of the American Society for Information Science and Technology, 34(1): 26-29. https://doi.org/10.1002/bult.2007.1720340108
  8. Choi, Y. and S. Y. Syn. 2016. "Characteristics of Tagging Behavior in Digitized Humanities Online Collections." Journal of the American Society for Information Science and Technology, 67(5): 1089-1104.
  9. Chung, E. and J. Yoon. 2010. "Examining Categorical Transition and Query Reformulation Patterns in Image Search Process." Journal of the Korean Society for Information Management, 27(2): 37-60. https://doi.org/10.3743/KOSIM.2010.27.2.037
  10. Dublin Core Metadata Initiative(DCMI). 2012. DCMI Type Vocabulary - DCMI Metadata Terms [online]. [cited 2017.9.12]. .
  11. Ewerth, R., M. Springstein, L. A. Phan-Vogtmann, and J. Schutze. 2017. "Are Machines Better Than Humans in Image Tagging? - A User Study Adds to the Puzzle." Advances in Information Retrieval, ECIR 2017, LNCS, 10193: 186-198.
  12. Golbeck, J., J. Koepfler, and B. Emmerling. 2011. "An experimental study of social tagging behavior and image content." Journal of the American Society for Information Science and Technology, 62(9): 1750-1760. https://doi.org/10.1002/asi.21522
  13. Hollink, L., A. Schreiber, B. J. Wielinga, and M. Worring. 2004. "Classification of user image descriptions." International Journal of Human-Computer Studies, 61(5): 601-626. https://doi.org/10.1016/j.ijhcs.2004.03.002
  14. Huang, H. 2006. "Tag distribution analysis using the power law to evaluate social tagging systems: A case study in the Flickr database." 17th ASIS&T SIG/CR Classification Research Workshop, 14-15.
  15. Huang, H. and C. Jorgensen. 2013. "Characterizing user tagging and co-occurring metadata in general and specialized metadata collections." Journal of the American Society for Information Science and Technology, 64(9): 1878-1889. https://doi.org/10.1002/asi.22891
  16. Jorgensen, C. 1998. "Attributes of images in describing tasks." Information Processing and Management, 34(2/3): 161-174.
  17. Jorgensen, C., A. Jaimes, A. B. Benitez, and S.-F. Chang. 2001, "A conceptual framework and empirical research for classifying visual descriptors." Journal of the American Society for Information Science and Technology, 52: 938-947.
  18. Jorgensen, C., B. Stvilia, and S. Wu. 2014. "Assessing the relationships among tag syntax, semantics, and perceived usefulness." Journal of the American Society for Information Science and Technology, 65(4): 836-849.
  19. Klavans, J. L., R. LaPlante, and J. Golbeck. 2014. "Subject matter categorization of tags applied to digital images from art museums." Journal of the Association for Information Science and Technology, 65(1): 3-12. https://doi.org/10.1002/asi.22950
  20. Li, X., C. G. M. Snoek, and M. Worring. 2009. "Annotating images by harnessing worldwide user-tagged photos." IEEE International Conference on Acoustics, Speech, and Signal Processing 2009.
  21. Lin, Y., C. Trattner, P. Brusilovsky, and D. He. 2015. "The impact of image descriptions on user tagging behavior: A study of the nature and functionality of crowdsourced tags." Journal of the American Society for Information Science and Technology, 66(9): 1785-1798.
  22. Marlow, C., M. Naaman, D. Boyd, and M. Davis. 2006. "HT06, tagging paper, taxonomy, Flickr, academic article, to read." Proceedings of the seventeenth conference on Hypertext and hypermedia (HYPERTEXT '06), 31-40.
  23. Nowak, S. and S. Ruger. 2010. "How reliable are annotations via crowdsourcing: a study about inter-annotator agreement for multi-label image annotation." Proceedings of the international conference on Multimedia information retrieval (MIR '10), 557-566.
  24. Panofsky, E. 1962. "Chapter I: Introductory. In Studies in iconology." Humanistic themes in the art of the Renaissance, 3-31.
  25. Ransom, N. and P. Rafferty. 2011. "Facets of user-assigned tags and their effectiveness in image retrieval." Journal of Documentation, 67(6): 1038-1066. https://doi.org/10.1108/00220411111183582
  26. Shatford, S. 1986. "Analyzing the subject of a picture: A theoretical approach." Cataloging & Classification Quarterly, 6(3): 39-62. https://doi.org/10.1300/J104v06n03_04
  27. Sigurbjornsson, B. and R. V. Zwol. 2008. "Flickr tag recommendation based on collective knowledge." Proceedings of the 17th International Conference on World Wide Web (WWW '08), 327-336.
  28. Smith, M. K. 2011. "Viewer tagging in art museums: Comparisons to concepts and vocabularies of art museum visitors." Advances in Classification Research Online, 17(1): 1-19.
  29. Spink, A. and B. J. Jansen. 2006. "Searching multimedia federated content web collections." Online Journal Review, 30(5): 485-495.
  30. Wang, M., B. Ni, X. Hua, and T. Chua. 2012. "Assistive tagging: A survey of multimedia tagging with human-computer joint exploration." ACM Computing Surveys, 44(4).
  31. Yoon, J. 2011. "Searching images in daily life." Library & Information Science Research, 33: 269-275.