Journal of Korea Game Society (한국게임학회 논문지)

Korea Game Society (한국게임학회)
권호 표지
DOI QR코드

DOI QR Code

Warping of 2D Facial Images Using Image Interpolation by Triangle Subdivision

삼각형 반복분할에 의한 영상 보간법을 활용한 2D 얼굴 영상의 변형

  • 김진모 (부산가톨릭대학교 소프트웨어학과) ;
  • 김종윤 (동국대학교 멀티미디어학과) ;
  • 조형제 (동국대학교 멀티미디어학과)
  • Received : 2014.03.18
  • Accepted : 2014.04.10
  • Published : 2014.04.20
Download PDF
⟨ Previous Next ⟩

Abstract

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.

영상 워핑은 입력 영상을 주어진 조건에 적합하게 변형하는 기술로, 최근 영화나 애니메이션 분야에서 캐릭터의 얼굴 형상을 변형하는데 활용되고 있다. 얼굴 특징을 기반으로 형상을 변형하는 워핑 방법 가운데 하나인 메쉬 워핑은 입력 영상에서 눈, 코, 입 주변의 사각형 모양의 메쉬 그룹을 형성하여 1:1정합시킴으로써 워핑 영상을 생성하는 방법이다. 이는 메쉬 제어점 좌표에 오차가 있거나 작은 면적의 메쉬로 세분화되어 생성된 경우 메쉬들의 경계 선분에서 결과 영상이 일그러지는 문제점이 있다. 본 연구는 얼굴의 자연스러운 워핑 영상을 생성하는 과정에서 오류 발생을 최소로 하며 정확한 결과를 적은 연산량과 시간에 처리하기 위해 삼각형기반의 영상 보간 기법을 제안한다. 우선 얼굴을 대표하는 특징점들을 찾고 이들을 연결하여 기본 삼각형 메쉬를 구성한다. 제안하는 방법은 기존의 메쉬 워핑과 비교하여 연산 처리량과 시간은 단축되면서 워핑 과정에서의 오류 발생을 줄일 수 있음을 실험으로 보인다.

Keywords

References

  1. M. Bleyer, M. Gelautz, C. Rother, and C. Rhemann, "A Stereo approach that handles the matting problem via image warping", Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2009, pp. 501-508, 2009.
  2. M. Kamali, A. Banno, J.C. Bazin, I.S. Kweon, and K. Ikeuchi, "Stabilizing omnidirectional videos using 3D structure and spherical image warping", Proceedings of the 12th IAPR Conference on Machine Vision Applications, pp. 177-180, 2011.
  3. Min-Gyu Choi, Seung-Yong Woo and Hyeong-Seok Ko, "An Extended Modal Warping Approach to Real-Time Simulation of Thin Shells", Journal of Korea Game Society, Vol. 7, No. 2, pp. 45-53, 2007.
  4. Jeongjin Lee, Moon-Koo Kang, Ho Lee and Byeong-Seok Shin, "Cloud Modeling Method of 2D Meteorological Satellite Images", Journal of Korea Game Society, Vol. 10, No. 1, pp. 147-156, 2010.
  5. D. Bonilla, and L. Velho, "Control Methods for Fluid-based image warping", Proceedings of XXIV Sibgrapi Conference on Graphics, Patterns and Images, 2011.
  6. G. Wolberg, "Digital image warping", IEEE Computer Society Press, 1990.
  7. J. Gomes, L. Darsa, B. Costa, and L. Velho, "Warping and morphing of graphical objects", Morgan Kaufmann Publ., 1999.
  8. A. H. Barr, "Global and local deformations of solid primitives", ACM SIGGRAPH Computer Graphics, Vol. 18, Issue 3, pp. 21-30, 1984. https://doi.org/10.1145/964965.808573
  9. S. Schaefer, T. McPhail, J. Warren, "Image deformation using moving least squares", ACM Trans. Graph., Vol. 25, Issue 3, pp. 533-540, 2006. https://doi.org/10.1145/1141911.1141920
  10. G. Wolberg, "Skeleton based image warping", Visual Computer, Vol. 5, No. 1/2, pp 95-108, 1989. https://doi.org/10.1007/BF01901485
  11. N. Arad and D. Reisfeld, "Image warping using few anchor points and radial functions", Computer Graphics Forum, Vol. 14, No. 1, pp. 35-46, 1995. https://doi.org/10.1111/1467-8659.1410035
  12. A. R. Smith, "Planar 2-pass texture mapping and warping", ACM SIGGRAPH Computer Graphics, Vol. 21, Issue 4, pp. 263-272, 1987. https://doi.org/10.1145/37402.37433
  13. Y. Weng, X. Shi, H. Bao, J. Zhang, "Sketching MLS image deformations on the GPU", Comput. Graph. Forum, Vol. 27, Issue 7, pp. 1789-1796, 2008. https://doi.org/10.1111/j.1467-8659.2008.01324.x
  14. H. Fang, J. C. Hart, "Detail preserving shape deformation in image editing", ACM Trans. Graph., Vol. 26, Issue 3, Article No. 12, 2007.
  15. T. Pereira, E. V. Brazil, I. Macedo, M. C. Sousa, L. H. de Figueiredo, and L. Velho, "Sketch-based warping of RGBN images", Graphical Models, Vol. 73, pp. 97-110, 2011. https://doi.org/10.1016/j.gmod.2010.11.001
  16. S. Schaefer, T. McPhail, J. Warren, "Image deformation using moving least squares", ACM Trans. Graph., Vol. 25, Issue 3, pp. 533-540, 2006. https://doi.org/10.1145/1141911.1141920
  17. W. A. Barrett, A. S. Cheney, "Object-based image editing", ACM Transactions on Graphics, Vol. 21, Issue 3, pp. 777-784, 2002.
  18. T. F. Coots, C. J. Taylor, D. Cooper, and J. Graham, "Active shape Models-Their Taining and Application", Computer Vision and Image Understanding, Vol. 61, No. 1, pp. 38-59, 1995. https://doi.org/10.1006/cviu.1995.1004
  19. M. Kass, A. Witkin, and D. Terzopoulos, "Snakes: Active Contour Models", International Journal of Computer Vision, Vol. 1, No. 4, pp. 321-331, 1988. https://doi.org/10.1007/BF00133570
  20. T. F. Cootes, Gareth J. Edwards, and Christopher J. Tayory, "Active Appearance Models", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 23, No. 6, pp. 681-658, 2001. https://doi.org/10.1109/34.927467
  21. Kitae Hwang, "Morphing and Warping using Delaunay Triangulation in Android Platform", Journal of Korea Game Society, Vol. 10, No. 6, pp. 137-146, 2010.