• Electronics and Telecommunications Trends
• /
• v.27 no.3
• /
• pp.12-21
• /
• 2012

최근 3DTV, 입체 모니터, 입체 노트북 등이 출시되고, 3D 영화, 게임 등 3D 관련 산업이 성장하면서 관련 콘텐츠의 요구사항이 증가하고 있다. 특히, 3D 콘텐츠의 주요 요소 중 하나인 인체는 전통적으로 고가의 3D 스캐너를 이용해 모델링하는 방식을 주로 사용해 왔다. 하지만 근래에는 광학 기술 및 컴퓨팅 성능의 향상으로 구조광과 같은 능동 센서나 카메라로부터 획득한 영상을 기반으로 3D 인체 외형을 복원하는 연구가 각광을 받고 있다. 이런 추세에 발맞춰 본고에서는 인체 중에서도 사용자의 민감도가 높은 얼굴의 3D 복원 기술 및 연구 동향을 살펴보고, 다양한 응용을 목적으로 ETRI에서 개발 중인 3D 얼굴 복원 기술을 소개하고자 한다.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.466-469
• /
• 2005

Recently, in computer graphics, researches on 3D animations have been very active. One of the important research areas in 3D animation is animation of human being. Implicit surface model is convient for modeling objects composed of complicated surface such as 3D characters and liquids. Moreover, it can represent various forms of surfaces using a relatively small amount of data. In this paper, we propose a method of facial model generation using Implicit Primitive.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1448-1450
• /
• 2015

본 논문은 3D 스캐너 및 센서 등으로 캡처되어 3D로 복원된 얼굴 객체의 부위별 의미 있는 영역에 대한 분할을 자동으로 수행하는 기술을 제안한다. 3D 스캔된 얼굴 모델을 모델링, 애니메이션, 3D 프린팅 등의 다양한 응용분야에 활용하기 위해서는 스캔된 영역의 의미 있는 부위별 인식이 필수적이다. 본 논문에서는 부위별 의미 있는 영역 레이블링이 된 템플릿 모델을 입력된 3D 복원 모델로 전이하여 복원된 3D 모델의 부위별 의미 있는 영역을 자동으로 분할하고 분할된 영역의 일관성을 유지하는 알고리즘을 제안한다.

• Journal of the Korea Computer Graphics Society
• /
• v.8 no.4
• /
• pp.17-25
• /
• 2002

In this paper we propose a new efficient muscle modeling for creating 3d facial models. It improves the existing muscle-based facial modeling method. We present the facial muscle action prediction map as a new method of muscle modeling. We also suggest a new face deformation method that improves the existing method which controls each muscle's condition separately.

• Journal of KIISE
• /
• v.43 no.5
• /
• pp.516-523
• /
• 2016

For old-age makeups, makeup artists first make a mold cast of an actor's face using plaster and then sculpt wrinkles in clay on the plaster mold. After finishing the clay sculpture, its negative plaster mold is fabricated and silicone skin patches are finally made for application to the actor's face. This process takes a few days and is tedious for actors and makeup artists. With recent advances in 3D printing and scanning technology, it is becoming easier to scan and fabricate 3D faces. This paper presents a new pipeline composed of facial scanning, interactive wrinkle modeling, and mold printing stages to easily and efficiently fabricate silicone masks for old-age makeups without the use of plaster and clay. An intuitive sketch interface based on a normal map is proposed for the creation of wrinkles in real time, even with a high-resolution face model. Then the geometry of the final wrinkles is reconstructed using a depth map and the negative mold of the wrinkled face is printed. We also show that the presented pipeline can fabricate a silicone mask more conveniently than the traditional one that consists of pouring silicone into the prepared negative mold and then overlapping the mold with the original positive one.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.01a
• /
• pp.47-49
• /
• 2011

본 논문에서는 사용자의 정면, 측면 영상을 이용하여 3차원 얼굴 모델에 적합한 텍스쳐 맵을 생성, 이를 이용하여 3차원 얼굴 모델을 생성하는 방법을 제안한다. 기존 3차원 얼굴 모델은 매핑 할 텍스쳐 영상들을 하나로 통합하여 이를 원통형 좌표계를 통해 텍스쳐링 하는 방법이 이용되고 있다. 이때 정면과 측면의 영상을 3차원 얼굴 모델의 중심축을 기준으로 계산하여 좌표에 맞게 투영시키고 통합 및 보간하여 텍스쳐링 하게 된다. 사용자는 이를 위하여 정면과 측면 영상을 원통형 좌표에 맞게 통합시키는 작업이 필요하다. 본 논문은 사용자에게 수반되는 이러한 작업을 줄이고 발생될 수 있는 텍스쳐의 왜곡을 최소화하기 위한 방법을 제시한다. 2차원 정면 측면 이미지를 3차원 얼굴모델에 투영시키고 정면과 측면을 구분하여 각 텍스쳐 간 경계 부분을 자연스럽게 처리하기 위해 파노라마 이미지 스티칭 기술을 이용하여 텍스쳐링 한 뒤 얼굴 모델을 생성하는 방법에 대해서 기술한다.

• Journal of the Korea Convergence Society
• /
• v.12 no.9
• /
• pp.57-63
• /
• 2021

This study dissected and three-dimensionally (3D) scanned the facial muscles of Korean adult cadavers, created a three-dimensional model with realistic facial muscle shapes, and reproduced facial expressions to provide educational materials to allow the 3D observation of the complex movements of cadaver facial muscles. Using the cadavers' anatomical photo data, 3D modeling of facial muscles was performed. We produced models describing four different expressions, namely sad, happy, surprised, and angry. We confirmed the complex action of the 3D cadaver facial muscles when making various facial expressions. Although the results of this study cannot confirm the individual functions of facial muscles quantitatively, we were able to observe the realistic shape of the cadavers' facial muscles, and produce models that would show different expressions depending on the actions performed. The data from this study may be used as educational materials when studying the anatomy of facial muscles.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.2
• /
• pp.328-333
• /
• 2003

This paper did to do with 18 muscle pairs that do fetters in anatomy that influence in facial expression change and mix motion of muscle for face facial animation. After set and change mash and make standard model in individual's image, did mapping to mash using individual facial front side and side image to raise truth stuff. Muscle model who become motive power that can do animation used facial expression creation correcting Waters' muscle model. Created deformed face that texture is dressed using these method. Also, 6 facial expression that Ekman proposes did animation.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.4
• /
• pp.41-48
• /
• 2015

Recently, the spread of 3D printers has been increasing the demand for 3D models. However, the creation of 3D models should have a trained specialist using specialized softwares. This paper is about an algorithm to produce a 3D model from a single sheet of two-dimensional front face photograph, so that ordinary people can easily create 3D models. The background and the foreground are separated from a photo and predetermined constant number vertices are placed on the seperated foreground 2D image at a same interval. The arranged vertex location are extended in three dimensions by using the gray level of the pixel on the vertex and the characteristics of eyebrows and nose of the nomal human face. The separating method of the foreground and the background uses the edge information of the silhouette. The AdaBoost algorithm using the Haar-like feature is also employed to find the location of the eyes and nose. The 3D models obtained by using this algorithm are good enough to use for 3D printing even though some manual treatment might be required a little bit. The algorithm will be useful for providing 3D contents in conjunction with the spread of 3D printers.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.42 no.6
• /
• pp.75-82
• /
• 2005

The robust feature vector selection method for the multiple frontal face detection is proposed in this paper. The proposed feature vector for the training and classification are integrated by means, amplitude projections, and its 1D Harr wavelet of the input image. And the statistical modeling is performed both for face and nonface classes. Finally, the estimated probability density functions (PDFs) are applied for the detection of multiple frontal faces in the still image. The proposed method can handle multiple faces, partially occluded faces, and slightly posed-angle faces. And also the proposed method is very effective for low quality face images. Experimental results show that detection rate of the propose method is $98.3\%$ with three false detections on the testing data, SET3 which have 227 faces in 80 images.