Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

On the Spatial Registration Considering Image Exposure Compensation

영상의 노출 보정을 고려한 공간 정합 알고리듬 연구

  • Kim, Dong-Sik (Department of Electronic and Information Engineering, Hankuk University of Foreign Studies) ;
  • Lee, Ki-Ryung (ECE, UIUC)
  • Published : 2007.03.25
Download PDF
⟨ Previous Next ⟩

Abstract

To jointly optimize the spatial registration and the exposure compensation, an iterative registration algorithm, the Lucas-Kanade algorithm, is combined with an exposure compensation algorithm, which is based on the histogram transformation function. Based on a simple regression model, a nonparametric estimator, the empirical conditional mean, and its polynomial fitting are used as histogram transformation functions for the exposure compensation. Since the proposed algorithm is composed of separable optimization phases, the proposed algorithm is more advantageous than the joint approaches of Mann and Candocia in the aspect of implementation flexibility. The proposed algorithm performs a better registration for real images than the case of registration that does not consider the exposure difference.

정합과 노출 보정을 동시에 최적화하기 위하여 반복적인 정합 알고리듬인 Lucas-Kanade 알고리듬을 히스토그램 변환에 기초한 노출 보정 알고리듬과 접목하였다. 단순 회귀 모델에 기초하여 비매개변수 추정인 실험적 조건 평균과 그의 다항식 근사를 이용하여 노출 보정을 시도하였다. 제안한 동시 최적화 알고리듬은 각 최적화 과정의 분리화가 가능하므로 기존의 Mann이나 Candocia의 동시 최적화 알고리듬에 비하여 구현의 융통성 측면에서 유리하다. 투사 공간 변환 관계를 가지는 실영상 들을 가지고 모의실험을 수행한 결과에서 보면 노출 보정을 고려하지 않은 경우에 비하여 좋은 성능을 얻음을 확인할 수 있었다.

Keywords

References

  1. J. Frank, Three-Dimensional Electron Microscopy of Macromolecular Assemblies. San Diego, CA: Academic, 1996
  2. S. Mann, 'Comparametric equations with practical applications in quantigraphic image processing,' IEEE Trans. Image Processing, vol. IP-9, no. 8, pp. 1389-1406, Aug. 2000
  3. L. G. Shapiro and G. C. Stockman, Computer Vision, NJ: Prentice Hall, 2001
  4. S. Mann, 'Pencigraphy with AGC: Joint parameter estimation in both domain and range of functions in same orbit of the projective-Wyckoff group', in Proc. IEEE Int. Conf. Image Processing, vol. 3, pp. 193-196, Sept. 1996
  5. F. M. Candocia, 'Jointly registering images in domain and range by piecewise linear comparametric analysis,' IEEE Trans. Image Processing, vol. IP-12, no. 4, pp. 409-419, April 2003
  6. T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning. NY: Springer, 2001
  7. B. Lucas and T. Kanade, 'An iterative image registration technique with an application to stereo vision,' in Proc. Imaging Understanding Workshop, pp. 121-130, 1981
  8. D. Luenberger, Linear and Nonlinear Programming, 2nd ed. MA: Addison-Wesley, 1984
  9. R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2nd. ed. NY: Prentice Hall, 2002
  10. R. E. Walpole, R. H. Myers, S. L. Myers, and K. Ye, Probability & Statistics for Engineers & Scientists, 7th. ed. NJ: Prentice Hall, 2002
  11. D. S. Kim and M. R. Bell, 'Upper bounds on empirically optimal quantizers,' IEEE Trans. Inform. Theory, vol. IT-49, no. 4, pp. 1037-1046, April 2003
  12. D. S. Kim, S. Y. Lee, and K. Lee, 'Empirical conditional mean: nonparametric estimator for comparametric exposure compensation,' in Proc. IEEE Int. Conf. Acoustics, Speech, Signal Processing, pp. II-957 - II-960, May 2006
  13. H. -Y. Shum and R. Szeliski, 'Construction and refinement of panoramic mosaics with global and local alignment,' in Proc. Int. Conf. Computer Vision, Bombay, Jan. 1998, pp. 953-958
  14. S. Baker and I. Matthews, 'A unifying framework: Part 1,' Tech. Report, CMU-RI-TR-02-16, Robotics Institute, Carnegie Mellon University, July 2002
  15. F. M. Candocia, 'Simultaneous homographic and comparametric alignment of multiple exposureadjusted pictures of the same scene,' IEEE Trans. Image Processing, vol. IP-12, no. 12, pp. 1485-1494, Dec. 2003