Journal of Broadcast Engineering (방송공학회논문지)

The Korean Institute of Broadcast and Media Engineers (한국방송∙미디어공학회)
권호 표지
DOI QR코드

DOI QR Code

Helper Classification via Three Dimensional Visualization of Character-net

Character-net의 3차원 시각화를 통한 조력자의 유형 분류

  • Park, Seung-Bo (Inha University, Dept. of Software Convergence Engineering) ;
  • Jeon, Yoon Bae (Inha University, Dept. of Information and Communication Engineering) ;
  • Park, Juhyun (Inha University, Dept. of Information and Communication Engineering) ;
  • You, Eun Soon (Inha University, Artificial Intelligent Content Creation Research Center)
  • 박승보 (인하대학교 소프트웨어융합공학과) ;
  • 전윤배 (인하대학교 정보통신공학과) ;
  • 박주현 (인하대학교 정보통신공학과) ;
  • 유은순 (인하대학교 인공지능 콘텐츠창작 연구센터)
  • Received : 2017.11.23
  • Accepted : 2017.12.12
  • Published : 2018.01.30
Download PDF
⟨ Previous Next ⟩

Abstract

It is necessary to analyze the character that are a key element of the story in order to analyze the story. Current character analysis methods such as Character-net and RoleNet are not sufficient to classify the roles of supporting characters by only analyzing the results of the final accumulated stories. It is necessary to study the time series analysis method according to the story progress in order to analyze the role of supporting characters rather than the accumulated story analysis method. In this paper, we propose a method to classify helpers as a mentor and a best friend through 3-D visualization of Character-net and evaluate the accuracy of the method. WebGL is used to configure the interface for 3D visualization so that anyone can see the results on the web browser. It is also proposed that rules to distinguish mentors and best friends and evaluated their performance. The results of the evaluation of 10 characters selected for 7 films confirms that they are 90% accurate.

스토리를 분석하기 위해서는 스토리의 행동 주체인 등장인물에 대한 분석이 선행되어야 한다. 현재의 등장인물 분석 방법인 Character-net이나 RoleNet과 같은 방법은 최종 누적된 스토리의 결과에 대한 분석만을 진행하여 조연의 역할 분류를 하기에는 부족한 면이 있다. 조연의 역할 분석을 위해 축적된 형태의 스토리 분석 방법이 아닌 스토리 진행에 따른 시계열적 분석 방법을 연구할 필요가 있다. 본 논문은 Character-net의 3차원 시각화를 통해 등장인물들 중에 조력자들을 유형에 따라 멘토와 단짝친구로 분류하는 방법을 제안하고 그 방법의 정확도를 평가하는 논문이다. 3차원 시각화를 위해 WebGL을 사용하여 웹브라우저 상에서 누구나 결과를 확인할 수 있도록 인터페이스를 구성하였다. 또한 멘토와 단짝친구를 구별하기 위한 규칙을 제안하였고 그 성능을 평가하였다. 영화 7편에 대해 선정된 10명의 등장인물에 대해 평가한 결과 90%의 정확도를 나타내는 것을 확인하였다.

Keywords

References

  1. S.-B. Park, K.-J. Oh, and G.-S. Jo, "Social Network Analysis in a Movie using Character -net," Multimedia Tools and Applications. vol. 59, no. 2, pp. 601-627, Jul. 2012. https://doi.org/10.1007/s11042-011-0725-1
  2. C. Y. Weng, W. T. Chu, and J. L. Wu, "RoleNet: movie analysis from the perspective of social network," IEEE Transaction on Multimedia, vol. 11, no. 2. pp. 256-271, 2009. https://doi.org/10.1109/TMM.2008.2009684
  3. Y. Tsivian, "Cinemetrics, Part of the Humanities' Cyberinfrastructure," Digital Tools in Media Studies: Analysis and Research: an Overview, Bielfeld: Transcript Verlag, pp. 93-100, 2009.
  4. C. E. Nothelfer, J. E. DeLong, and J. E. Cutting, "Shot Structure in Hollywood Film," Indiana Undergraduate Journal of Cognitive Science, vol. 4, pp. 103-113, 2009.
  5. F. Brodbeck, Cinemetrics, http://cinemetrics.fredericbrodbeck.de
  6. Aristotele, Plato, Dionysius Longinus, Aristoteles's Poetics, (translated by Cheon Myeong Hui), Moonyebooks, 2002.
  7. Y. Lim, (2016). "The Climax Expression Analysis Based on the Shot-list Data of Movies," Journal of Broadcast Engineering, vol. 21, no. 6, pp. 965-976. Jul. 2016. https://doi.org/10.5909/JBE.2016.21.6.965
  8. J. Campbell, The Hero with A Thousand Faces, (translated by Lee Yoon Ki), Minumsa, 2004.
  9. C. Vogler, The Writer's Journey, (translated by Ham Choon Sung), Bizandbiz, 2007.
  10. H. C. Kwan, Story Generation System in the Digital Storytelling : Focused on 'Story Engine Modelling, Korea National University of Arts, 2010.
  11. D. Marks, Inside Story: The Power of the Transformational Arc, Methuen Drama, 2006.
  12. V. L. Schmid, 45 Master Characters, (translated by Nam Gil Young), Badabooks, Oct. 2017.
  13. M. Kim, Z. Lee, and W. Kim, "Realtime Human Object Segmentation Using Image and Skeleton Characteristics," Journal of Broadcast Engineering, vol. 21, no. 5, Sep. 2016.
  14. I.-K. Choia, H. Song, S. Lee, and J. Yoo, "Facial Expression Classification Using Deep Convolutional Neural Network," Journal of Broadcast Engineering, vol. 22, No. 2, Mar. 2017.
  15. S.-B. Park, H. N. Kim, H. Kim, and G. S. Jo, "Exploiting Script-Subtitles Alignment to Scene Boundary Dectection in Movie," 2010 IEEE International Symposium on Multimedia(ISM), pp. 49-56, Dec. 2010.