Journal of the Korea Computer Graphics Society (한국컴퓨터그래픽스학회논문지)

Korea Computer Graphics Society (한국컴퓨터그래픽스학회)
권호 표지

Acceleration of Feature-Based Image Morphing Using GPU

GPU를 이용한 특징 기반 영상모핑의 가속화

  • Kim, Eun-Ji (Department of Multimedia, Dongguk University) ;
  • Yoon, Seung-Hyun (Department of Multimedia Engineering, Dongguk University) ;
  • Lee, Jieun (Department of Computer Engineering, Chosun University)
  • 김은지 (동국대학교 영상대학원 멀티미디어학과) ;
  • 윤승현 (동국대학교 영상대학원 멀티미디어공학과) ;
  • 이지은 (조선대학교 컴퓨터공학과)
  • Received : 2014.05.13
  • Accepted : 2014.05.29
  • Published : 2014.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, a graphics-processing-unit (GPU)-based acceleration technique is proposed for the feature-based image morphing. This technique uses the depth-buffer of the graphics hardware to calculate efficiently the shortest distance between a pixel and the control lines. The pairs of control lines between the source image and the destination image are determined by user's input, and the distance function of each control line is rendered using two rectangles and two cones. The distance between each pixel and its nearest control line is stored in the depth buffer through the graphics pipeline, and this is used to conduct the morphing operation efficiently. The pixel-unit morphing operation is parallelized using the compute unified device architecture (CUDA) to reduce the morphing time. We demonstrate the efficiency of the proposed technique using several experimental results.

본 논문에서는 특징 기반 영상모핑(feature-based image morphing)을 위한 GPU (Graphics Processing Unit) 기반의 가속화 기법을 제시한다. 제안된 기법은 모핑과정에서 픽셀과 제어선 사이의 최단거리를 효율적으로 계산하기 위해 그래픽스 하드웨어의 깊이 버퍼(depth-buffer)를 이용한다. 먼저 원본영상(source image)과 최종영상(destination image)에 사용자입력을 통해 특징을 표현하는 제어선들을 지정하고, 각 제어선의 거리함수(distance function)를 서로 다른 색상을 갖는 두개의 사각형과 원뿔로 렌더링한다. 그래픽스 파이프라인(graphics pipeline)을 통해 각 픽셀에서 가장 가까운 제어선까지의 거리는 깊이 버퍼에 저장되고, 이는 모핑연산을 효율적으로 수행하는데 사용된다. 본 논문에서는 픽셀 단위의 모핑 연산을 CUDA(Compute Unified Device Architecture)를 이용하여 병렬화함으로써 모핑의 속도를 더욱 향상시키며, 다양한 크기의 입력영상에 대하여 각각 CPU와 GPU를 이용한 영상모핑 실험을 통해 제안된 기법의 효율성을 입증한다.

Keywords

References

  1. T. Beier and S. Neely, "Feature-based image metamorphosis," SIGGRAPH Comput. Graph., vol. 26, pp. 35-42, July 1992. https://doi.org/10.1145/142920.134003
  2. T. J. True and J. F. Hughes, "Volume warping," in Proceedings of the 3rd conference on Visualization '92, ser. VIS '92. Los Alamitos, CA, USA: IEEE Computer Society Press, 1992, pp. 308-315.
  3. G.Wolberg, Digital Image Warping, 1st ed. IEEE Computer Society Press, 1994.
  4. S. Lee, K.-Y. Chwa, and S. Y. Shin, "Image metamorphosis using snakes and free-form deformations," in SIGGRAPH 95 Proceedings of the 22th annual conference on Computer graphics and interactive techniques. ACM Press/Addison- Wesley Publishing Co., 1995, pp. 439-448.
  5. R. Crane, Simplified Approach to Image Processing: Classical and Modern Techniques in C, 1st ed. Prentice Hall PTR, 1996.
  6. S. Lee, G. Wolberg, and S. Y. Shin, "Polymorph: morphing among multiple images," IEEE Computer Graphics and Applications, vol. 18, no. 1, pp. 58-71, 1998.
  7. M. Alexa, D. Cohen-Or, and D. Levin, "As-rigid-aspossible shape interpolation," in Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, ser. SIGGRAPH '00. New York, NY, USA: ACM Press/Addison-Wesley Publishing Co., 2000, pp. 157-164. [Online]. Available: http://dx.doi.org/10.1145/344779.344859
  8. S. Schaefer, T. McPhail, and J. Warren, "Image deformation using moving least squares," ACM Trans. Graph., vol. 25, no. 3, pp. 533-540, July 2006. [Online]. Available: http://doi.acm.org/10.1145/1141911.1141920
  9. S. N. Sinha, J. M. Frahm, M. Pollefeys, and Y. Genc, "Feature tracking and matching in video using programmable graphics hardware," Mach. Vision Appl., vol. 22, pp. 207-217, January 2011. https://doi.org/10.1007/s00138-007-0105-z
  10. M.-H. Lee and I.-K. Park, "Accelerating Depth Image-Based Rendering Using GPU," Journal of KISS : Computer Systems and Theory, vol. 33, no. 11,12, pp. 853-858, 2006.
  11. D. B. Kirk andW. meiW. Hwu, Programming Massively Parallel Processors: A Hands-on Approach, 1st ed. Morgan Kaufmann, 2010.
  12. J. Sanders and E. Kandrot, CUDA by Example: An Introduction to General-Purpose GPU Programming, 1st ed. Addison Wesley, 2010.
  13. T. Ren, Y. Liu, and G. Wu, 'Image retargeting using multimap constrained region warping," in Proceedings of the 17th ACM international conference on Multimedia, ser. MM '09. New York, NY, USA: ACM, 2009, pp. 853-856.
  14. S. Karungaru, M. Fukumi, and N. Akamatsu, "Autometic face metamorphosis in color images," in Proc. of 2005 RISP International Workshop on Nonlinear Circuits and Signal Processing, 2005, pp. 131-134.
  15. M.-H. Yang, D. J. Kriegman, and N. Ahuja, "Detecting faces in images: A survey," IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, pp. 34-58, January 2002. https://doi.org/10.1109/34.982883
  16. K.-H. Shin, M.-J. Kwon, K.-P. Min, J. chul Chun, and M.- H. Kim, "Automatic method for feature based 2d face image morphing," Korean Society For Internet Information Conference, vol. 6, no. 2, pp. 149-153, 2005.
  17. Y. Wei, "Research on facial expression recognition and synthesis," Master Thesis, Department of Computer Science and Technology, Nanjing University, February 2009.
  18. A.-J. Park, H.-H. Jang, and K.-C. Jung, "Fast and efficient implementation of neural networks using cuda and openmp," Journal of KISS : Software and Applications, vol. 36, no. 4, pp. 253-260, 2009.
  19. S.-I. Choi, S.-Y. Park, J. Kim, and Y.-W. Park, "Multiview range image registration using cuda," Journal of KISS, vol. 35, no. 1C, pp. 533-538, 2008.
  20. J.-H. Song, S.-H. Kang, G.-M. Kim, and B.-S. Kim, "A study of the application of delaunay grid generation on gpu using cuda library," Journal of Korean Society of Computational Fluids Engineering, pp. 194-198, 2011.
  21. M. Zamith, A. Montenegro, E. Passos, E. Clua, A. Conci, R. Leal-Toledo, and P. Mourao, "Real time feature-based parallel morphing in gpu applied to texture-based animation," in Systems, Signals and Image Processing, 2009. IWSSIP 2009. 16th International Conference on, 2009, pp. 1-4.
  22. K. E. Hoff, III, J. Keyser, M. Lin, D. Manocha, and T. Culver, "Fast computation of generalized voronoi diagrams using graphics hardware," in SIGGRAPH 99 Proceedings of the 26th annual conference on Computer graphics and interactive techniques. ACM Press/Addison-Wesley Publishing Co., 1999, pp. 277-286.
  23. Y.-J. Kim, J. Lee, M.-S. Kim, and G. Elber, "Efficient offset trimming for planar rational curves using biarc trees," Computer Aided Geometric Design, vol. 29, no. 7, pp. 555-564, 2012. https://doi.org/10.1016/j.cagd.2012.03.014