• Title/Summary/Keyword: Korean animation

Search Result 1,481, Processing Time 0.021 seconds

Comparative Analysis of Markerless Facial Recognition Technology for 3D Character's Facial Expression Animation -Focusing on the method of Faceware and Faceshift- (3D 캐릭터의 얼굴 표정 애니메이션 마커리스 표정 인식 기술 비교 분석 -페이스웨어와 페이스쉬프트 방식 중심으로-)

  • Kim, Hae-Yoon;Park, Dong-Joo;Lee, Tae-Gu
    • Cartoon and Animation Studies
    • /
    • s.37
    • /
    • pp.221-245
    • /
    • 2014
  • With the success of the world's first 3D computer animated film, "Toy Story" in 1995, industrial development of 3D computer animation gained considerable momentum. Consequently, various 3D animations for TV were produced; in addition, high quality 3D computer animation games became common. To save a large amount of 3D animation production time and cost, technological development has been conducted actively, in accordance with the expansion of industrial demand in this field. Further, compared with the traditional approach of producing animations through hand-drawings, the efficiency of producing 3D computer animations is infinitely greater. In this study, an experiment and a comparative analysis of markerless motion capture systems for facial expression animation has been conducted that aims to improve the efficiency of 3D computer animation production. Faceware system, which is a product of Image Metrics, provides sophisticated production tools despite the complexity of motion capture recognition and application process. Faceshift system, which is a product of same-named Faceshift, though relatively less sophisticated, provides applications for rapid real-time motion recognition. It is hoped that the results of the comparative analysis presented in this paper become baseline data for selecting the appropriate motion capture and key frame animation method for the most efficient production of facial expression animation in accordance with production time and cost, and the degree of sophistication and media in use, when creating animation.

A Study on Improvement for User Participation in Web based Animation-creating Applications (웹 기반 애니메이션 제작 어플리케이션의 개선 방법 연구)

  • Choo, Yeon-Jun;Suk, Hae-Jung
    • Cartoon and Animation Studies
    • /
    • s.21
    • /
    • pp.33-49
    • /
    • 2010
  • Since the Web 2.0 generation, the average user is more than just enjoying the various media contents; they start to create contents, and those contents have had a huge value and great influence in recent days. The reason for the increase of users who tend to create contents is due to popularization of web based applications. Previous applications were only for the skilled person; however, new web based applications involve the average person and give him a new level of user enjoyment by allowing him to create easily with simple operations. In this paper, through analysing previous animation-creating applications which could not spread widely compared to other contents, we suggest the outline for developing a web based animation-creating application which can help the user to easily create animation contents. We have looked around at how various other contents-making applications have been changed to help the user to be able to participate in creating contents, and we suggest how animation-creating applications can be changed and developed from this analysis. We expect the conclusion of this paper to stimulate to development acting 3D animation-creating applications corresponding to the web 2.0 features - open, share, cooperate, participate. In result, users can enjoy creating the animation more actively; at the same time, we hope to help the development of the new applications which correlate to memedia generation.

  • PDF

Factorial analysis on commercial success of the American theatrical CG animation movies : Focused on characters, situations, and images (미국 극장용 CG애니메이션의 흥행 요인 분석: 인물, 상황, 이미지를 중심으로)

  • Chang, Wook-Sang;Han, Boo-Young
    • Cartoon and Animation Studies
    • /
    • s.30
    • /
    • pp.59-86
    • /
    • 2013
  • 'Spectacles' and 'factuality' provided by computer technology are strengths of CG animation to still lure the audience and after commercial success of a number of theatrical CG animations whose typical producing companies are PIXAR and DreamWorks, were produced to be commercially successful and they win massive popularity even now. In Korea as well, several works tried to achieve a box office success including , , etc. but the result was truly miserable. In the past, this failure was often attributed to a lack of 'technical expertise', but it became clear that in the process of continuous trial and error, 'narrative' and 'images of imagination' which are bases and characteristics of animation are key elements of commercial success. Actually, statistics indicate that narrative is what is considered to be the most important by the audience when they select animation and its importance is so absolute that they say the most significant thing in animation is 'story.' In particular, it can be said that 'characters', 'situations', and 'ideas' play a key role in them which become elements of the story. This paper studied with what characteristics each animation aroused pleasure and fun focused on characters, situations and images in relation to , , and which are American theatrical CG animation films which succeeded in gaining popularity home and abroad. We hope that analysis in this paper will be helpful even just a little bit as a reference material, which allows domestic writers and producers to develop familiar and characteristic works based on imagination and creativity expressing each work's unique personality and characteristics.

A Study on the Visual Style of Animation Documentary Genre (애니메이션 다큐멘터리의 시각적 스타일에 관한 연구)

  • Jung, Hye-kyung;Kim, Hye-kyung
    • Cartoon and Animation Studies
    • /
    • s.42
    • /
    • pp.25-52
    • /
    • 2016
  • Animation documentary is a hybrid genre that is newly highlighted with opposite properties. The actual world is reproduced with an unrealistic method in documentary aspect, but the objectivity of documentaries cannot be guaranteed as the boundary of actual pictures and digital images has become ambiguous. As the animation documentary by Ari Folman succeeded in 2008, the focus of this study is on 'how can fictional animations prove the authenticity of documentaries?' in which the study is mainly conducted in documentary aspect. For this, the researcher considers visual style research has important role in understanding and developing a new video genre, and asserts the necessity of research on reproduction image that is produced by the characteristics of animation which is produced in frame units. This paper has contents on the visual style of animation documentaries with pictorial reproduction methods in which animation images were classified into 3 styles based on previous research on animation documentary style. Visual styles are classified into actual image that is based on similarity with reality to deliver objective facts, image that is transformed through emphasis and omission which are factors of animations, and surrealistic image that reproduces non-visual regions such as illusions and the inner side of characters. Through this study that analyzes visual style types and characteristics, animation documentaries are expected to position as a hybrid genre that illustrates reality with a new method instead of being included in the existing reproduction method of documentaries.

A Study on Korean Speech Animation Generation Employing Deep Learning (딥러닝을 활용한 한국어 스피치 애니메이션 생성에 관한 고찰)

  • Suk Chan Kang;Dong Ju Kim
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.12 no.10
    • /
    • pp.461-470
    • /
    • 2023
  • While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.