한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

  • 제20권4호
  • /
  • Pages.41-48
  • /
  • 2015
  • /
  • 1598-849X(pISSN)
  • /
  • 2383-9945(eISSN)
한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

얼굴 2D 이미지의 3D 모델 변환 알고리즘

An Algorithim for Converting 2D Face Image into 3D Model

  • 최태준 (부산외국어대학교 ICT 창의융합학과) ;
  • 이희만 (서원대학교 멀티미디어학과)
  • Choi, Tae-Jun (Dept. of Creative ICT Engineering, Busan University of Foreign Studies) ;
  • Lee, Hee-Man (Dept. of Multimedia Engineering, Seowon University)
  • 투고 : 2015.03.03
  • 심사 : 2015.04.16
  • 발행 : 2015.04.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 3D 프린터의 보급과 함께 3D 모델에 대한 수요가 급증하고 있다. 그러나 3D 모델의 생성은 숙달된 전문가가 전문 소프트웨어를 이용하여 작성하여야 한다. 본 연구는 한 장의 2차원 정면 얼굴사진으로 부터 3D 모델링하는 방법에 대한 것으로 일반인들도 쉽게 3D모델을 생성할 수 있도록 한다. 사진으로부터 배경과 전경을 분리하고 분리한 전경 영역에 일정간격으로 2차원 상에 버텍스를 배치하고 배치한 버텍스 위치를 이미지의 계조 값과 눈썹과 코 등의 특성을 고려하여 버텍스를 3차원으로 확장한다. 전경과 배경을 분리하는 방법으로 에지정보를 사용하였으며 눈과 코의 위치를 찾기 위하여 Haar-like feature를 이용하는 AdaBoost 알고리즘을 사용하였다. 알고리즘으로 생성한 3D 모델은 수작업에 의한 후처리가 필요하지만 3D 프린터를 위한 콘텐츠 제공에 매우 유용하게 활용될 것이다.

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.

키워드

참고문헌

  1. Choi Chang-seok, Chou, Young-Jin, "Classification of Fundermental Types of Korean Faces and Generation of the Faces for Each Province," Institude of Electronics and Information Engineers, Vol.15, No.2, 1997.
  2. D.DeCarlo, D.Metaxas and Matthew Stone, "An Antropometric Face Model Using Variational Techniques," Computer Graphics(SIGGRAPH 98 Proceedings), pp.67-74, 1998.
  3. K. Waters. "A Muscle Model for Animating Three-Dimension Facial Expression," In Proceeding of SIGGRAPH 87, Vol.21, No.4, pp.117-124, July 1987.
  4. Y.C.Lee, D.Terzopoulos, and K.Waters, "Realistic Modeling for Facial Animation," In SIGGRAPH 95 Conference Proceedings, pp.55-62, August 1995.
  5. Seok-Woo Jang, "Estimation of 3D Rotation Information of AnimationCharacter Face," Journal of the Korea Society of Computer and Information, Vol.16, No.8, pp.49-55, 2011. https://doi.org/10.9708/jksci.2011.16.8.049
  6. Seok-Woo Jang, "Synthesizing Faces of Animation Characters Using a 3D Model," Journal of the Korea Society of Computer and Information, Vol.17, No.8, pp.31-40, 2012. https://doi.org/10.9708/jksci.2012.17.8.031
  7. Chris Boehnen,Patrick Flynn,"Accuracy of 3D Scanning Technologies in a Face Scanning Scenario," Fifth International Conference on 3-D Digital Imaging and Modeling, pp.310-317, 2005.
  8. Sang-Myung Kim, Chang-Han Park, "Face Feature Extraction Method Through Stereo Image's Matching Value," Journal of Korea Multimedia Society, Vol.8, No.4(1), pp.461-472, 2005.
  9. Sungpil Moon, "Study on Industrializing Stereoscopic 3D Image Generated from 2D Image," MyongJi Univ. Graduate School, Ph.D. Thesis, Dept. Industrial Engineering, 2011.
  10. Seitz, S.M.,Curless, B., "A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, June, Vol.1 pp.17-22, 2006.
  11. Berthold K.P. Horn, "Shape From Shading: A Method For Obtaining The Shape Of A Smooth Opaque Object From One View," MIT AI Lab Technical Report #232, 1970.
  12. Ruo Zhang, Ping-Sing Tsai, "Shape from Shading: A Survey," IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 21, No. 8, Aug., 1999.
  13. Ruben Garcia-Zurdo, "Three-dimensional Face Shape By Local Feature Prediction," International J. of Image Processing(IJIP), Vol. 9 No.1, 2015.
  14. Viola and Jones, "Rapid object detection using boosted cascade of simple features," Computer Vision and Pattern Recognition, pp.1-9, 2001.
  15. Yoav Freund, Robert E. Schapire, "A Decision-Th eoretic Generalization of on-Line Learning and an Application to Boosting," Vol.904, pp.23-37, 1995.

피인용 문헌

  1. 2D이미지의 3D 모델화 알고리즘 적용을 통한 인터랙티브 수족관개발 vol.18, pp.12, 2015, https://doi.org/10.9717/kmms.2015.18.12.1562