Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

The Method to Estimate Saliency Values using Gauss Weight

가우스 가중치를 이용한 돌출 값 추정을 위한 방법

  • 유영중 (부산외국어대학교 컴퓨터공학과)
  • Received : 2013.02.04
  • Accepted : 2013.03.05
  • Published : 2013.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

It is important work to extract saliency regions from an image as preprocessing for various image processing methods. In this paper, we introduce an improved method to estimate saliency value of each pixel from an image. The proposed method is an improved work of the previously studied method using color and statistical framework to estimate saliency values. At first, saliency value of each pixel is calculated using the local contrast of an image region at various scales and the most significant saliency pixel is determined using saliency value of each pixel. Then, saliency value of each pixel is again estimated using gauss weight with respect to the most significant saliency pixel and the saliency of each pixel is determined to calculate initial probability. At last, the saliency value of each pixel is calculated by Bayes' rule. The experiments show that our approach outperforms the current statistical based method.

이미지로부터 돌출 영역을 추출하는 것은 이후의 다양한 이미지 처리를 위한 사전 작업으로서 중요한 의미를 가진다. 이 논문에서는 하나의 이미지에서 각 픽셀의 돌출 값을 추정하기 위한 개선된 방법을 소개한다. 논문에서 제안되는 방법은 이전에 연구된 색상과 통계적 방법을 이용한 돌출 값 추정 방법을 개선한 방법이다. 먼저 이미지에서 픽셀들의 색상관계를 이용해 각 픽셀의 돌출 값을 계산하고, 이 값을 근거로 중심 돌출 픽셀을 추정한다. 추정된 중심 돌출 픽셀을 기준으로 가우스 가중치를 적용하여 각 픽셀의 돌출 값을 재추정하고, 통계적 돌출 값 추정에 적용할 초기 확률을 위해 각 픽셀의 돌출 여부가 결정된다. 마지막으로 각 픽셀의 돌출 값은 베이즈 확률을 사용하여 계산된다. 실험결과는 본 논문의 적용 방법이 적정한 크기의 돌출 영역을 가진 이미지에 대해 이전의 방법보다 우수한 결과를 보임을 보여준다.

Keywords

References

  1. Y. F. Ma and H. J. Zhang, "Contrast-base image attention analysis by using fuzzy growing," Proc. 11th ACM International Conference on Multimedia, pp. 374-381, 2003.
  2. V. Setlur, S. Takagi, R. Raskar, M. Gleicher and B. Gooch, "Automatic image retargeting," Proc. 4th International Conference on Mobile and Ubiquitous Multimedia, pp. 59-68, 1997.
  3. S. Avidan and A. Shamir, "Seam carving for contentaware for image resizing," ACM Transactions on Graphics, vol. 26, no. 3, 2007.
  4. Y. Sheikh and M. Shah, "Bayesian modeling of dynamic scenes for object detection," IEEE TPAMI, vol. 27, no. 11, 2005.
  5. A. Monnet, A. Mittal, N. Paragios and V. Ramesh, "Background modeling and subtraction of dynamic scenes," CVPR, vol. 2, pp. 1305-1312, 2003.
  6. C. Lampert, M. Blaschko and T. Hofmann, "Efficient subwindow search: A branch and bound framework for object localization," IEEE TPAMI, vol. 31, pp. 2129-2142, 2009. https://doi.org/10.1109/TPAMI.2009.144
  7. C. Desai, D. Ramanan and C. Fowlkes, "Discriminative models for multi-class object layout," ICCV, pp. 229-236, 2009.
  8. L. Itti, C. Koch and E. Niebur, "A model of saliency-based visual attention for rapid scene analysis," IEEE TPAMI, vol. 20, pp. 1254-1259, 1998. https://doi.org/10.1109/34.730558
  9. D. Walther and C. Koch, "Modeling attention to salient proto-objects," Neural Netw., vol. 19, pp. 1395-1407, 2006. https://doi.org/10.1016/j.neunet.2006.10.001
  10. R. Achanta, F. Estrada, P. Wils and S. Susstrunk, "Salient region detection and segmentation," Proc. ICVS, pp. 66-75, 2008.
  11. E. Rahtu and J. Heikkila, "A simple and efficient saliency detector for background subtraction," IEEE 12th ICCV, pp. 1137-1144, 2009.
  12. E. Rahtu, J. Kannala, M. Salo and J. Heikkila, "Segmenting salient objects from image and videos," Proc. ECCV, pp. 366-379, 2010.
  13. Seong-Ho Park and Young-Jung Yu, "The Method to Measure Saliency Values for Salient Region Detection from an Image," International Journal of KIMICS, vol. 9, no. 1, pp. 55-58, 2011. https://doi.org/10.6109/jicce.2011.9.1.055