• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.699-707
• /
• 1999

It cannot be argued that speech is the most natural interfacing tool between men and machines. In order to realize acceptable speech interfaces, highly advanced speech recognizers and synthesizers are inevitable. Text-to-Speech(TTS) technology has been attracting a lot of interest among speech engineers because of its own benefits. Namely, the possible application areas of talking computers, emergency alarming systems in speech, speech output devices fur speech-impaired, and so on. Hence, many researchers have made significant progresses in the speech synthesis techniques in the sense of their own languages and as a result, the quality of currently available speech synthesizers are believed to be acceptable to normal users. These are partly why the MPEG group had decided to include the TTS technology as one of its MPEG-4 functionalities. ETRI has made major contributions to the current MPEG-4 TTS among various MPEG-4 functionalities. They are; 1) use of original prosody for synthesized speech output, 2) trick mode functions fer general users without breaking synthesized speech prosody, 3) interoperability with Facial Animation(FA) tools, and 4) dubbing a moving/animated picture with lib-shape pattern information.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2002.04a
• /
• pp.265-268
• /
• 2002

얼굴은 성별, 나이, 인종에 따라 다양한 특징을 가지고 있어서 개개인을 구별하기가 쉽고 내적인 상태를 쉽게 볼 수 있는 중요한 도구로 여겨지고 있다. 본 논문은 얼굴표정 애니메이션을 위한 효과적인 방법으로 실제얼굴의 피부조직 얼굴 근육 등 해부학적 구조에 기반한 근육기반모델링을 이용하는 방법을 소개하고자 한다. 제안하는 시스템의 구성은 얼굴 와이어프레임 구성과 폴리곤 메쉬분할 단계, 얼굴에 필요한 근육을 적용시키는 단계, 근육의 움직임에 따른 얼굴 표정생성단계로 이루어진다. 와이어프레임 구성과 폴리곤 메쉬 분할 단계에서는 얼굴모델을 Water[1]가 제안한 얼굴을 기반으로 하였고, 하나의 폴리곤 메쉬를 4등분으로 분할하여 부드러운 3D 얼굴모델을 보여준다. 다음 단계는 얼굴 표정생성에 필요한 근육을 30 개로 만들어 실제로 표정을 지을 때 많이 쓰는 부위에 적용시킨다. 그 다음으로 표정생성단계는 FACS 에서 제안한 Action Unit 을 조합하고 얼굴표정에 따라 필요한 근육의 강도를 조절하여 더 자연스럽고 실제감 있는 얼굴표정 애니메이션을 보여준다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2000.10b
• /
• pp.919-922
• /
• 2000

본 논문에서는 가상 인터페이스로서 범용적으로 사용할 수 있는 실시간 비전 기반 얼굴 애니메이션을 제안한다. 이를 위해서 실시간으로 얼굴 구성요소를 추출하고, 이를 정량화 하였다. 정량화된 값과 자연스럽게 매핑하기 위해서 정합함수를 통해 3차원 모델에 맵핑하기 위한 방안을 제안한다. 일반적으로 3차원 애니메이션을 수행할 경우, 기본 모델을 중심으로 특정한 사용자만을 위주로 수행되나, 본 논문에서는 임의의 일반 사용자를 위한 3차원 애니메이션을 수행하였다. 여러 사용자에 대하여 얼굴 구성요소 추출을 이용한 3차원 얼굴 애니메이션 동작에 대하여 실험하였으며 실험결과 여러 사용자 얼굴 애니메이션 동작에 대하여 만족할 만한 성능을 보였다.

• Proceedings of the Korea Contents Association Conference
• /
• 2018.05a
• /
• pp.49-50
• /
• 2018

본 논문은 깊이 이미지 이용한 페이셜 애니메이션 제작 방법을 소개한다. iPhone X의 true depth카메라를 사용하여 사람 얼굴의 심도를 정확하게 파악하고, 균등하게 분산된 도트를 통해 얼굴의 모든 표정변화를 모바일 데이터로 기록하여, 페이셜 애니메이션을 제작하는 제작한다. 본문에서의 방식은, 기존 페이셜 애니메이션 제작 과정에서의 rigging 부분을 생략하여, 기록된 얼굴 표정 데이터를 3D 모델링에 바로 전달할 수 있다. 이런 방식을 통해 전체 페이셜 애니메이션 제작 과정을 단축시켜, 제작 방법을 더욱 간단하고 효율적이게 하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2012.06c
• /
• pp.323-325
• /
• 2012

스마트폰 기반 3D 아바타를 이용하여 임의의 표정을 합성 및 제어하여 애니메이션 할 수 있는 방법과 응용을 제안한다. 사용될 아바타에 표현되는 임의의 표정 Data Set을 PCA로 처리 후, 인간의 가장 기본적인 6 표정으로 컨트롤러 축을 생성한다. 만들어진 제어기에, 임의의 연속 표정을 유저에 의해 정해진 시간에 생성하여 애니메이션 할 수 있는 방법을 시스템을 제안하다. 빠른 계산을 장점으로 하는 본 제어기는 스마트폰 환경에 맞게 탑재 되었으며, 이 제어기를 활용하여 모델워킹 모션에 다양한 표정을 적용할 수 있는 시스템을 구현하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.8
• /
• pp.1255-1258
• /
• 2022

Recently, immersive VR/AR contents have actively increased, and various services related to VR/AR allow users to experience remote places. For example, if failure situations occur frequently in factory of the remote site, mixed reality (MR) with a synthetic virtual human expert in reconstructed remote location can help immediate maintenance task with interaction between the operator and the virtual expert. In this paper, we present a technique for synthesizing the virtual human after capturing a 360-degree panorama of a remote environment, and analyze the effects to apply a method of guiding virtual human by interaction types. According to this paper, it was shown that co-presence level significantly increased when verbal, facial expression, and non-verbal animation of the virtual human was all expressed.

• Journal of the Korea Computer Graphics Society
• /
• v.15 no.1
• /
• pp.7-15
• /
• 2009

In this paper, a novel framework that synthesizes and clones facial expression in parameter spaces is presented. To overcome the difficulties in manipulating face geometry models with high degrees of freedom, many parameterization methods have been introduced. In this paper, a data-driven parameterization method is proposed that represents a variety of expressions with a small set of fundamental independent movements based on the ICA technique. The face deformation due to the parameters is also learned from the data to capture the nonlinearity of facial movements. With this parameterization, one can control the expression of an animated character's face by the parameters. By separating the parameterization and the deformation learning process, we believe that we can adopt this framework for a variety applications including expression synthesis and cloning. The experimental result demonstrates the efficient production of realistic expressions using the proposed method.

• The Journal of the Korea Contents Association
• /
• v.7 no.5
• /
• pp.63-71
• /
• 2007

From several commercialized games the technique of changing facial expressions is imported, and a design method of a game character for the player's empathy is expected to be diversified in the future. In this paper, as a design method of a game character for the player's empathy, this makes walking motion for the game character applied with 'human-emotion' factors as statistics variation of a game character in RPG genre. After this paper implements analyzed emotions of human facial expression and walking motions applied with emotion in examples of character animation theory, this paper divides walking motion applied with human-emotion factors into 8 types through relationship to statistics factors in RPG genre. And then these are applied to a knight character, which has the most similarity with human's physical feature of the game characters in RPG genre, and makes walking motion as variable statistics. As a game player controls the game character applied with 'human-emotion' factors, the effect of the player's empathy about the game character becomes higher, and the level of immersion in game play is also expected to increase.

• Journal of Korea Game Society
• /
• v.14 no.2
• /
• pp.55-66
• /
• 2014

Image warping is a technology to transform input images to be suitable for given conditions and has been recently utilized in changing face shape of characters in the field of movies or animation. Mesh warping which is one of warping methods that change shapes based on the features of face forms warping images by forming rectangular mesh groups around the eyes, nose, and mouth and matching them 1:1. This method has a problem in the resultant images are distorted in the segments of boundaries between meshes when there are errors in mesh control points or when meshes have been formed as many small area meshes. This study proposes a triangle based image interpolation technique to minimize the occurrence of errors in the process of forming natural warping images of face and process accurate results with a small amount of arithmetic operation and a short time. First, feature points that represent the face are found and these points are connected to form basic triangle meshes. The fact that the proposed method can reduce errors occurring in the process of warping while reducing the amount of arithmetic operation and time is shown through experiments.

• Archives of Plastic Surgery
• /
• v.41 no.1
• /
• pp.12-18
• /
• 2014

In patients having a short nose with a short septal length and/or severe columellar retraction, a septal extension graft is a good solution, as it allows the dome to move caudally and pushes down the columellar base. Fixing the medial crura of the alar cartilages to a septal extension graft leads to an uncomfortably rigid nasal tip and columella, and results in unnatural facial animation. Further, because of the relatively small and weak septal cartilage in the East Asian population, undercorrection of a short nose is not uncommon. To overcome these shortcomings, we have used the septal extension graft combined with a derotation graft. Among 113 patients who underwent the combined procedure, 82 patients had a short nose deformity alone; the remaining 31 patients had a short nose with columellar retraction. Thirty-two patients complained of nasal tip stiffness caused by a septal extension graft from previous operations. In addition to the septal extension graft, a derotation graft was used for bridging the gap between the alar cartilages and the septal extension graft for tip lengthening. Satisfactory results were obtained in 102 (90%) patients. Eleven (10%) patients required revision surgery. This combination method is a good surgical option for patients who have a short nose with small septal cartilages and do not have sufficient cartilage for tip lengthening by using a septal extension graft alone. It can also overcome the postoperative nasal tip rigidity of a septal extension graft.