The Journal of the Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회논문지)

The Institute of Internet, Broadcasting and Communication (한국인터넷방송통신학회)
권호 표지
DOI QR코드

DOI QR Code

Image Reconstruction Using Poisson Model Screened from Image Gradient

이미지 기울기에서 선별된 포아송 모델을 이용한 이미지 재구성

  • Kim, Yong-Gil (Dept.of computer Security, Chosun college of science & technology)
  • 김용길 (조선이공대학교 컴퓨터보안과)
  • Received : 2018.01.15
  • Accepted : 2018.04.06
  • Published : 2018.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we suggest a fast image reconstruction scheme using Poisson equation from image gradient domain. In this approach, using the Poisson equation, a guided vector field is created by employing source and target images within a selected region at the first step. Next, the guided vector is used in generating the result image. We analyze the problem of reconstructing a two-dimensional function that approximates a set of desired gradients and a data term. The joined data and gradients are able to work like modifying the image gradients while staying close to the original image. Starting with this formulation, we have a screened Poisson equation known in physics. This equation leads to an efficient solution to the problem in FFT domain. It represents the spatial filters that solve the two-dimensional screened Poisson model and shows gradient scaling to be a well-defined sharpen filter that generalizes Laplace sharpening. We demonstrate the results using a discrete cosine transformation based this Poisson model.

본 연구에서는 이미지 기울기 영역에서 포아송 방정식을 이용한 빠른 이미지 재구성 기법을 제안한다. 포아송 방정식을 사용하는 이 접근법에서, 유도된 벡터 필드는 제 1 단계에서 선택된 영역 내에서 원본과 대상 이미지를 사용함으로써 생성된다. 다음으로, 유도된 벡터는 결과 이미지를 생성하는데 사용된다. 우리는 원하는 기울기 집합과 데이터 항을 근사화하는 2차원 함수를 재구성하는 문제를 분석했다. 결합된 데이터와 기울기는 원본 이미지에 가깝게 머무르는 동안 이미지 기울기를 수정하는 것처럼 작동 할 수 있다. 이 공식으로부터 우리는 물리학에서 알려진 포아송 방정식을 찾아냈다. 이 방정식은 FFT 도메인의 문제에 대한 효율적인 해결책을 제시한다. 이것은 2차원으로 알려진 포아송 모델을 해결하고 기울기 비례축소는 라플라스를 확실하게 일반화하는 잘 정의된 선명한 필터임을 공간 필터에 잘 나타냅니다. 포아송 모델을 기반으로 이산 코사인 변환을 사용하여 결과를 확인할 수 있었다.

Keywords

References

  1. P. Bhat, L. Zitnick, M. Cohen, and B. Curless, "A perceptually-motivated optimization-framework for image and video processing" Technical Report UWCSE-08-06-02, University of Washington, 2008. DOI: https://doi.org/10.1.1.308.9598
  2. B. Dizdaroglu, and C. Ikibaş, "A seamless image editing technique using color information" in IPCV'09: International Conf. on Image Processing, Computer Vision & Pattern Recognition, Las Vegas, USA. July 13-16, 2009.
  3. Q. Chuan, W. Shuozhong, and Z. Xinpeng, "Image editing without color inconsistency using modified poisson equation" in International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp. 397-401, Aug. 2008. DOI: https://doi.org/10.1109/IIH-MSP.2008.28
  4. R. Fattal, D. Lischinski, and M. Werman, "Gradient domain high dynamic range compression" in Proceedings of ACM SIGGRAPH 2002, Vol. 21, No. 3, pp. 249-256, July 2002. DOI: https://doi.org/10.1145/566654.566573
  5. T. Georgiev, "Covariant derivatives and vision" ECCV 2006, 9th European Conference on Computer Vision, Graz, Austria, pp. 56-69, May 7-13, 2006.
  6. T. Georgiev, "Photoshop healing brush: a tool for seamless cloning" In Workshop on Applications of Computer Vision in conjunction with ECCV 2004, pp.1-8, Jan 2004. DOI: https://doi.org/10.1.1.109.5521
  7. T. Georgiev, "Image reconstruction invariant to relighting" in EUROGRAPHICS, pp. 61-64, 2005. DOI: https://doi.org/10.2312/egs.20051024
  8. J. Jia, J. Sun, C. Tang, and H. Shum, "Drag-and-drop pasting" in International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH, Vol. 25, No. 3, pp. 631-636, Jul 2006. DOI: https://doi.org/10.1145/1141911.1141934
  9. D. Leventhal, and P. G. Sibley, "Poisson image editing extended" in International Conference on Computer Graphics and Interactive Techniques, ACM SIGGRAPH, pp.313-318, Jul 30-Aug 03, 2006. DOI: https://doi.org/10.1145/1179622.1179712
  10. P. Perez, M. Gangnet, and A. Blake, "Poisson image editing" ACM Trans. Graph. Vol. 22. No. 3. pp. 313-318, Jul 2003, DOI: https://doi.org/10.1145/882262.882269
  11. J. Sun, J. Jia, C. K. Tang, and H. Y. Shum, "Poisson matting" ACM Trans. Graph. Vol. 23, No.3, pp.315-321, Aug, 2004. DOI: https://doi.org/10.1145/1015706.1015721
  12. J. Shen, X. Jin, C. Zhou, and C. C. L. Wang, "Gradient based image completion by solving the Poisson equation" Comput Graph. Vol 31, No. 1, pp. 119-126, 2007. DOI: https://doi.org/10.1016/j.cag.2006.10.004
  13. W. Yang, J. Zheng, J. Cai, S. Rahardja, and C. W. Chen, "Natural and seamless image composition with color control" IEEE Trans Image Process. Vol. 18, No. 11, pp. 2584-2592, 2009. DOI: https://doi.org/10.1109/TIP.2009.2027365
  14. M. R. Willett, Z. T. Harmany, and R. F. Marcia, "Poisson image reconstruction with total variation regularization" Image Processing (ICIP), 2010 17th IEEE International Conference on Source: IEEE Xplore, 2010. DOI: https://doi.org/10.1109/ICIP.2010.5649600
  15. G. Kim, K.I. Moon, "Image Restoration Based on Inverse Filtering Order and Power Spectrum Density", The Journal of The Institute of Internet, Broadcasting and Communication(JIIBC), Vol. 16 No. 2, pp.113-122, April 2016. DOI: http://dx.doi.org/10.7236/JIIBC.2016.16.2.113