Browse > Article
http://dx.doi.org/10.9717/kmms.2020.24.2.336

Study on AI-based content reproduction system using movie contents  

Yang, Seokhwan (Institute of Image and Cultural Contents, Dongguk University)
Lee, Young-Suk (Institute of Image and Cultural Contents, Dongguk University)
Publication Information
Journal of Korea Multimedia Society / v.24, no.2, 2021 , pp. 336-343 More about this Journal
Abstract
AI technology is spreading not only to industrial fields, but also to culture, art, and content fields. In this paper, we proposed a system based on AI technology that can automate the process of reproducing contents using characters for movie contents. After creating the basic appearance of the character by using the StyleGAN2 model from the video extracted from the movie contents, analyzing the character's personality and propensity using the extracted dialogue data, it was determined from the contemplative appearance based on the yin-yang and five elements to the character's propensity. Accordingly, the external characteristics are reflected in the character. Using the OpenPose model, a character's motion is created, and the finally generated data is integrated to reproduce the content. It is expected that many movie contents can be reproduced through the study of the proposed system.
Keywords
AI; Movie Contents; Character Creation; OpenPose; Reproduction;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 IITP, Emotion recognition technology trend, Weekly ICT Trends, Vol. 1868, 2018.
2 IDG Custom Content Services, Reading emotions in writing: Understanding emotion analysis, IDG Tech Report, 2014.
3 Deep learning starts with speech recognition: Voice recognition and signal processing (2019). https://wikidocs.net/30647 (accessed January 10, 2021).
4 Naver unveils 'NEST' AI speech recognition technology that accurately recognizes long or complex sentences(2020). https://www.aitimes.kr/news/articleView.html?idxno=16032 (accessed January 10, 2021).
5 ETRI, Research Trends for Deep LearningBased High-P erformance Face Recognition Technology, Electronics and Telecommunications Trends, Vol. 33, No. 4, 2018.
6 Move Mirror: You move and 80,000 images move with you(2018). https://www.blog.googl e/technology/ai/move-mirror-you-move-and80000-images-move-you/ (accessed January 10, 2021).
7 L.A. Gaty, A.S. Ecker, and M. Bethge, "A Neural Algorithm of Artistic Style," arXiv:1508. 06576v2 [cs.CV], 2015.
8 S.S. Kang, H.J. Won, and M.H. Lee, "Analyzing Vocabulary Characteristics of Colloquial Style Corpus and Automatic Construction of Sentiment Lexicon," Smart Media Journal, Vol. 9, No. 4, pp. 144-151, 2020.
9 Personality Insight(2016). https://personalityinsights-demo.ng.bluemix.net/ (accessed January 10, 2021).
10 S.R. Cho, H. Shin, Y.B. Jang, S.E. Lee, M.W. Han, and B.C. Koo, "A Case Study of Broadcasting Contents Using One Source Multi Use Strategy," Journal of Broadcast Engineering, Vol. 12, No. 5, pp. 423-434, 2007.   DOI
11 T. Karras, S. Laine, and T. Aila, "A Style-Based Generator Architecture for Generative Adversarial Networks," arXiv:1812. 04948v3 [cs.NE], 2019.
12 T. Karras, S. Laine, M. Aittala, J. Hellsten, J. Lehtinen, and T. Aila, "Analyzing and Improving the Image Quality of StyleGAN," arXiv:1912.04958v2 [cs.CV], 2020.
13 H.W. Kang, S.H. Ha, M.G. Lee, D.Y. Jeong, and D.W. Jeong, "Classifying the Vocabulary for Emotional Expressions of Korean Language using a Card Sorting Method," Proceedings of 2019 Fall Conference of Ergonomics Society of Korea, pp. 24-28, 2019.
14 S.H. Hong and J.H. Kim, "A Study on Animation Character Face Design System Based on Physiognomic Judgment of Character Study in the Cosmic Dual Forces and the Five Elements Thoughts," Journal of Korea Mutimedia Society, Vol. 9, No. 7, pp. 872-893, 2006.
15 S.H. Hong and M.J. Kim, "A Study of 2D Avatar's Game Character Expression Design System based on Physiognomic Judgment of Character Study," Proceeding of the Fall Conference of the Korea Multimedia Society, pp. 365-368, 2009.
16 H.Y. Ko, J.S. Lee, and J.H. Kim, "Character's Facial Expression Realization Program with Emotional State Dimensions," The J ournal of the Korea Institute of Maritime Information & Communication Sciences, Vol. 12, No. 3, pp. 438-444, 2008.
17 NIA, Changes and Prospects of Culture and Arts in Intelligent Information Society, Information Culture Issue Report, Vol. 16, No. 3, 2016.
18 Z. Cao, G. Hidalgo, T. Simon, S.E. Wei, and Y. Sheikh, "OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 43, No. 1, pp. 172-186, 2021.   DOI