The KIPS Transactions:PartB (정보처리학회논문지B)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Acquisition of Intrinsic Image by Omnidirectional Projection of ROI and Translation of White Patch on the X-chromaticity Space

X-색도 공간에서 ROI의 전방향 프로젝션과 백색패치의 평행이동에 의한 본질 영상 획득

  • 김달현 (충북대학교 컴퓨터공학과) ;
  • 황동국 (충북대학교 컴퓨터공학과) ;
  • 이우람 (충북대학교 컴퓨터공학과) ;
  • 전병민 (충북대학교 전기전자컴퓨터공학부)
  • Received : 2010.06.30
  • Accepted : 2011.01.14
  • Published : 2011.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Algorithms for intrinsic images reduce color differences in RGB images caused by the temperature of black-body radiators. Based on the reference light and detecting single invariant direction, these algorithms are weak in real images which can have multiple invariant directions when the scene illuminant is a colored illuminant. To solve these problems, this paper proposes a method of acquiring an intrinsic image by omnidirectional projection of an ROI and a translation of white patch in the ${\chi}$-chromaticity space. Because it is not easy to analyze an image in the three-dimensional RGB space, the ${\chi}$-chromaticity is also employed without the brightness factor in this paper. After the effect of the colored illuminant is decreased by a translation of white patch, an invariant direction is detected by omnidirectional projection of an ROI in this chromaticity space. In case the RGB image has multiple invariant directions, only one ROI is selected with the bin, which has the highest frequency in 3D histogram. And then the two operations, projection and inverse transformation, make intrinsic image acquired. In the experiments, test images were four datasets presented by Ebner and evaluation methods was the follows: standard deviation of the invariant direction, the constancy measure, the color space measure and the color constancy measure. The experimental results showed that the proposed method had lower standard deviation than the entropy, that its performance was two times higher than the compared algorithm.

흑체의 온도 변화에 대한 영상의 색차를 줄이는 본질 영상은 단일 불변 방향을 검출하고 백색 장면 조명체를 기반으로 하기 때문에 실영상에 존재하는 다수의 불변 방향과 유색 장면 조명체에 취약하다. 이러한 문제를 해결하기 위해 본 논문에서는 ${\chi}$-색도 공간에서 ROI의 전방향프로젝션과 백색패치의 평행이동을 통해 불변 방향을 검출하는 본질 영상 획득 기법을 제안한다. 3차원 RGB 공간 분석의 어려움으로 인하여, 본 논문 또한 밝기가 고려되지 않은 ${\chi}$-색도 공간을 사용한다. 이 공간에서 유색 조명체의 효과는 백색패치의 평행이동을 통해 감소시키고, 색차에 따라 가상의 선분으로 나타나는 불변 방향은 ROI의 전방향 프로젝션을 통해 검출한다. 다수의 불변 방향을 고려하여 ROI 선택은 3D 히스토그램에서 빈도수에 의해 결정한다. 검출 후, 본질 영상은 불변 방향의 직교 방향으로의 프로젝션과 RGB영상으로의 역변환 과정을 통해 획득된다. 실험에서 Ebner가 제안한 데이터집합을 실험 영상으로 이용하였고, 불변 방향의 표준편차와 색항등성 측도를 평가 측도로 사용하였다. 제안한 기법의 실험 결과는 엔트로피 기법보다 불변 방향의 표준 편차가 낮았으며, 기존의 기법에 비해 색항등성이 2배 이상 높았다.

Keywords

References

  1. S. Zeki, 'A Vision of the Brain', Oxford, Blackwell Science, 1993.
  2. M. Ebner, "A parallel algorithm for color constancy," Journal of Paralled and Distributed Computing, Vol.64, No.1, pp.79-88, 2004. https://doi.org/10.1016/j.jpdc.2003.06.004
  3. M. Ebner, Color Constancy, WILEY, 2007.
  4. J. P. Renno, D. Makris, T. Ellis, and G. A. Jones, "Application and Evaluation of Colour Constancy in Visual Surveillance," Proceedings of the 14th International Conference on Computer Communications and Networks, pp.301-308, 2005. https://doi.org/10.1109/VSPETS.2005.1570929
  5. S. D. Hordley, "Scene Illuminant Estimation: Past, Present, and Future," Color Research and Application, Vol.31, No.4, pp.303-314, August, 2006. https://doi.org/10.1002/col.20226
  6. G. D. Finlayson and S. D. Hordley, "Color constancy at a pixel," Journal of the Optical Society of America, Vol.18, No.2, pp.253-264, 2001. https://doi.org/10.1364/JOSAA.18.000253
  7. G. D. Finlayson, M. S. Drew and C. Lu, "Intrinsic images by entropy minimization," Proceedings of the 8th European Conference on Computer Vision, Part III, Prague, pp.582-595, 2004.
  8. M. S. Drew, G. D. Finalyson, and S. D. Hordley, "Recovery of chromaticity image free from shadows via illumination invariance," ICCV'03 Workshop on Color and Photometric Methods in Computer Vision, Nice, pp.32-39, 2003.
  9. M. F. Tappen, W. T. Freeman, and E. H. Adelson, "Recovering Intrinsic images from a single image," Technical Report AI Memo 2002-015, MIT, Artificial Intelligence Laboratory, 2002.
  10. He Qiang and Henry Chu Chee-Hung, "Recovering Intrinsic images from Weighted Edge Maps," Second International Conference on Intelligent Information Hiding and Multimedia Signal Processing, pp.159-162, 2006.
  11. M. Ebner, "Evolving color constancy," Special Issue on Evolutionary Computer Vision and Image Understanding of Pattern Recognition Letters, Vol.27, No.11, pp.1220-1229, 2006.
  12. H. Haken and H. C. Wolf, "Atom-und Quantenphysik: Einfv hrung in die Experimentellen und Theoretischen Grundlagen," vierte edn, Springer-Verlag, Berlin, Heidelberg, 1990.
  13. B. Jahne, Digitale Bildverarbeitung, fifth edn, Springer-Verlag, Berlin, 2002.
  14. G. D. Finlayson and M. S. Drew, "4-Sensor Camera Calibration for Image Representation Invariant to Shading, Shadows, Lighting, and Specularities," Proceedings of the Eighth IEEE Internatinal Conference on Computer Vision, Vol.2, pp.473-480, 2001. https://doi.org/10.1109/ICCV.2001.937663
  15. K. Barnard, L. Martin, B. Funt and A. Coath, "A data set for color research," Color Research and Applications, Vol.27, No.3, pp.148-152, 2002.
  16. M. Ebner, "Color Constancy Based on Local Space Average Color," Machine Vision and Applications, Vol.11, No.5, pp.283-301, July, 2009.