The Journal of the Korea Contents Association (한국콘텐츠학회논문지)

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Obtaining Object by Using Optimal Threshold for Saliency Map Thresholding

Saliency Map을 이용한 최적 임계값 기반의 객체 추출

  • ;
  • 김도연 (전남대학교 전자컴퓨터공학과) ;
  • 박혁로 (전남대학교 전자컴퓨터공학과)
  • Received : 2011.03.02
  • Accepted : 2011.04.15
  • Published : 2011.06.28
Download PDF
⟨ Previous Next ⟩

Abstract

Salient object attracts more and more attention from researchers due to its important role in many fields of multimedia processing like tracking, segmentation, adaptive compression, and content-base image retrieval. Usually, a saliency map is binarized into black and white map, which is considered as the binary mask of the salient object in the image. Still, the threshold is heuristically chosen or parametrically controlled. This paper suggests using the global optimal threshold to perform saliency map thresholding. This work also considers the usage of multi-level optimal thresholds and the local adaptive thresholds in the experiments. These experimental results show that using global optimal threshold method is better than parametric controlled or local adaptive threshold method.

이미지로부터 중요 객체를 추출하는 것은 추적, 분할, 적응적 압축, 내용기반 검색과 같은 멀티미디어 처리에 있어서 매우 중요한 부분이며, 현재 이에 관한 많은 연구가 진행 되고 있다. 중요 객체 추출을 위한 방법으로 Saliency Map을 이용한 방법이 있다. 이 방법에서는 일반적으로 이진화된 Saliency Map을 이용하여 어떤 화소가 중요 객체 내부인가 아닌가를 표시한다. 따라서 이 방법은 이진화를 위한 임계값의 선택이 성능에 매우 중요한 영향을 끼친다. 기존 연구에서는 일반적으로 휴리스틱 방법을 이용하여 임계값을 결정하거나 매개변수로 임계값을 조정하는 방법이 사용되었다. 그러나 하나의 임계값 적용은 이미지 안의 다수의 객체가 포함되어 있는 경우 적합하지 않다. 본 논문에서는 이러한 단점을 개선할 수 있는 Otsu 임계값을 이용한 전역적인 최적 임계값을 사용하는 방법을 제안한다. 제안하는 Otsu 임계화 방법은 단일-계층에 적용할 수 있는 Otsu 방법과 이를 확장하여 다중-계층에도 적용할 수 있는 Otsu 방법이다. 제안한 방법을 기존의 Saliency Map 모델에 적용한 결과 성능이 개선되었음을 확인하였다.

Keywords

References

  1. L. Itti, C. Koch, and E. Niebur, "A Model of Saliency-Based Visual Attention for Rapid Scene Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.20, No.11 pp.1254-1259, 1998. https://doi.org/10.1109/34.730558
  2. N. Ouerhani, A. Bur, and H. Hugli, "Linear vs. Nonlinear Feature Combination for Saliency Computation: A Comparison with Human Vision," Lecture Notes in Computer Science, Vol.4174, pp.314-323, 2006. https://doi.org/10.1007/11861898_32
  3. N. Ouerhani and H. Hugli, "MAPS : Multiscale Attention-Based PreSegmentation of Color Images," Lecture Notes in Computer Science, Vol.2695, pp.537-549, 2003. https://doi.org/10.1007/3-540-44935-3_37
  4. Y. Hu, X. Xie, W. Y. Ma, L. T. Chia, and D. Rajan, "Salient Region Detection Using Weighted Feature Maps Based on the Human Visual Attention Model," Lecture Notes in Computer Science, Vol.3332, pp.993-1000, 2004. https://doi.org/10.1007/978-3-540-30542-2_122
  5. N. Otsu, "A threshold selection method from gray level histograms," IEEE Trans. Systems, Man and Cybernetics, Vol.9, No.1, pp.62-66, 1979. https://doi.org/10.1109/TSMC.1979.4310076
  6. M. Merler and J. R. Kender, "Semantic Keyword Extraction via Adaptive Text Binarization of Unstructured Unsourced Video," In Proceedings of IEEE International Conference on Image Processing (ICIP 2009), Cairo, 2009. https://doi.org/10.1109/ICIP.2009.5413432
  7. R. Achanta and S. Susstrunk, "Saliency Detection for Content-aware Image Resizing," In Proceedings of IEEE International Conference on Image Processing (ICIP 2009), Cairo, 2009. https://doi.org/10.1109/ICIP.2009.5413815
  8. L. Chen, X. Xie, X. Fan, W. Y. Ma, H. J. Zhang, and H. Q. Zhou, "A visual attention mode for adapting images on small displays," ACM Transactions on Multimedia Systems, Vol.9, No.4, pp.353-364, 2003. https://doi.org/10.1007/s00530-003-0105-4
  9. J. Harel, C. Koch, and P. Perona "Graph-Based Visual Saliency," Advances in Neural Information Processing Systems, Vol.19, pp.545-552, 2007.
  10. R. Achanta, S. Hemami, F. Estrada, and S. Susstrunk, "Frequency-tuned salient region detection," In Proceedings of IEEE Conference on, Computer Vision and Pattern Recognition (CVPR 2009), Miami, pp.1597-1604, 2009. https://doi.org/10.1109/CVPR.2009.5206596
  11. R. Achanta, F. Estrada, P. Wils, and S. Susstrunk "Salient Region Detection and Segmentation," In Proceedings of International Conference on Computer Vision Systems (ICVS 2008), pp.66-75, 2008. https://doi.org/10.1007/978-3-540-79547-6_7
  12. X. Hou and L. Zhang, "Saliency Detection: A Spectral Residual Approach," In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (ICVS 2007), pp.1-8, 2007. https://doi.org/10.1109/CVPR.2007.383267
  13. P. S. Liao, T. S. Chen, and P. C. Chung, "A fast algorithm for multilevel thresholding," Journal of Information Science and Engineering, Vol.17, No.5, pp.713-727, 2001.
  14. http://research.microsoft.com/en-us/um/people/jiansun/SalientObject/salient_object.htm.
  15. T. Liu, J. Sun, N. N. Zheng, X. Tang, and H. Y. Shum, "Learning to Detect A Salient Object," In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2007), pp.1-8, 2007. https://doi.org/10.1109/CVPR.2007.383047

Cited by

  1. Multi-view Image Generation using Grid-mesh based Image Domain Warping and Occlusion Region Information vol.18, pp.6, 2013, https://doi.org/10.5909/JBE.2013.18.6.859