Skip to main content
SpringerLink
Log in

A saliency model based on wavelet transform and visual attention

  • Research Papers
  • Published:
Science China Information Sciences Aims and scope Submit manuscript

Abstract

This paper presents a novel wavelet transform saliency model to detect salient objects. In this model, a saliency map is generated by combining orientation feature maps obtained from wavelet transform of different scale images derived from the same image. Then, the order map of a saliency map is obtained by using Fourier descriptor, which could be used as a guidance to process the most important objects. Experiments indicate that this saliency model is robust to noise and superior to other saliency models in the literature.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. von Grünau M, Iordanova M. Visual selection: Facilitation due to stimulus saliency. In: Proceedings of the II Workshop on Cybernetic Vision, Sao Carlos, Brazil, 1996. 15-20

  2. Niebur E, Koch C. Computational architectures for attention. In: Parasuraman R, ed. The Attentive Brain. Cambridge: MIT Press, 1998. 163–186

    Google Scholar 

  3. Gilles S. Robust description and matching of Images. PhD thesis. Oxford of Britain: University of Oxford, 1998

    Google Scholar 

  4. Loupias E, Sebe N, Bres S, et al. Wavelet-based salient points for image retrieval. IEEE Conf Image Process, Vancouver, BC, Canada, 2000, 2: 518–521

    Google Scholar 

  5. Kingsbury N G. Complex wavelets for shift invariant analysis and filtering of signals. Appl Comput Harmon Anal, 2001, 10: 234–253

    Article  MATH  MathSciNet  Google Scholar 

  6. Fauqueur J, Kingsbury N, Anderson R. Multiscale keypoint detection using the Dual-Tree complex wavelet transform. In: IEEE Conf Image Processing, Atlanta, GA, USA, 2006. 1625–1628

  7. Laurent C, Laurent N, Maurizot M, et al. In depth analysis and evaluation of saliency-based color image indexing methods using wavelet salient features. Multimed Tools Appl, 2006, 31: 73–94

    Article  Google Scholar 

  8. Mikolajczyk K, Schmid C. An affine invariant interest point detector. In: Proceedings of the European Conference on Computer Vision, London: Springer-Verlag, 2002. 128–142

    Google Scholar 

  9. Schmid C, Mohr R, Bauckhage C. Evaluation of interest point detectors. Int J Comput Vision, 2000, 37: 151–172

    Article  MATH  Google Scholar 

  10. Sebe N, Lew M S. Comparing salient point detectors. Pattern Recogn Lett, 2003, 24: 89–96

    Article  MATH  Google Scholar 

  11. Carson C, Belongie S, Greespan H, et al. Blobworld: image segmentation using expectationmaximization and its application to image querying. IEEE Trans Pattern Anal Mach Intell, 2002, 24: 1026–1038

    Article  Google Scholar 

  12. Wang J Z, Li J, Wiederhold G. Simplicity: semantics-sensitive integrated matching for picture libraries. IEEE Trans Pattern Anal Mach Intell, 2001, 23: 947–963

    Article  Google Scholar 

  13. Shokoufandeh A, Marsic I, Dickinson S J. View-based object recognition using saliency maps. Image Vision Comput, 1999, 17: 445–460

    Article  Google Scholar 

  14. Kadir T. Scale, Saliency, Scene Description. PhD thesis. Oxford of Britain: University of Oxford, 2001

    Google Scholar 

  15. Kadir T, Brady M. Saliency, scale and image description. Int J Comput Vision, 2001, 45: 83–105

    Article  MATH  Google Scholar 

  16. Itti L, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis. IEEE Trans Pattern Anal Mach Intell, 1998, 20: 1254–1259

    Article  Google Scholar 

  17. Itti L, Koch C. Feature combination strategies for saliency-based visual attention systems. J Electr Imag, 2001, 10: 161–169

    Article  Google Scholar 

  18. Hou X D, Zhang L Q. Saliency detection: A spectral residual approach. In: IEEE Conf Computer Vision and Pattern Recognition, Minneapolis, MN, 2007. 1–8

  19. Wilson H R. Psychophysical models of spatial vision and hyperacuity. Spatial Vision, 1991, 10: 64–81

    Google Scholar 

  20. Daly S J. The visible differences predictor: an algorithm for the assessment of image fidelity. In: Watson A B, ed. Digital Images and Human Vision. Cambridge: MIT Press, 1993. 179–206

    Google Scholar 

  21. Lubin J. A visual discrimination model for imaging system design and evaluation. In: Peli E, ed. Vision Models for Target Detection, World Scientific Publishing, 1995. 245–283

  22. Pattanaik S N, Fairchild M D, Ferwerda J A, et al. Multiscale model of adaptation, spatial vision and color appearance. In: The Sixth Color Imaging Conference: Color Science, Systems and Applications, Scottsdale, 1998. 2–7

  23. Hopf J M, Boehler C N, Luck S J, et al. Direct neurophysiological evidence for spatial suppression surrounding the focus of attention in vision. Proc Natl Acad Sci USA, 2006, 103: 1053–1058

    Article  Google Scholar 

  24. Cutzu F, Tsotsos J K. The selective tuning model of attention: psychophysical evidence for a suppressive annulus around an attended item. Vision Res, 2003, 43: 205–219

    Article  Google Scholar 

  25. Paffen C L, van der Smagt M J, te Pas S F, et al. Center-surround inhibition and facilitation as a function of size and contrast at multiple levels of visual motion processing. J Vision, 2005, 5: 571–578

    Article  Google Scholar 

  26. Mallat S G. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell, 1989, 11: 674–693

    Article  MATH  Google Scholar 

  27. Daubechies I. Ten Lectures on Wavelets. Philadelphia: Society for Industrial and Applied Mathematics, 1992

    MATH  Google Scholar 

  28. Levitt J B, Lund J S. Contrast dependence of contextual effects in primate visual cortex. Nature, 1997, 387: 73–76

    Article  Google Scholar 

  29. Nothdurft H C. Saliency effects across dimensions in visual search. Vision Res, 1993, 33: 839–844

    Article  Google Scholar 

  30. Nothdurft H C. Salience from feature contrast: additivity across dimensions. Vision Res, 2000, 40: 1183–1201

    Article  Google Scholar 

  31. Petkovic T, Krapac J. Shape description with Fourier descriptors. Tehnical Report. 2002

  32. Kunttu I, Lepistö L, Rauhamaa J, et al. Multiscale Fourier descriptors for defect image retrieval. Pattern Recogn Lett, 2006, 27: 123–132

    Article  Google Scholar 

  33. Chun S L, Chia H L. New forms of shape invariants from elliptic fourier descriptors. Pattern Recogn, 1987, 20: 535–545

    Article  Google Scholar 

  34. Kim H K, Kim J D. Region-based shape descriptor. invariant to rotation, scale and translation. Signal Process Imag, 2000, 16: 87–93

    Article  Google Scholar 

  35. Mokhtarian F, Mackworth A K. Scale-based description and recognition of planar curves and two-dimensional shapes. IEEE Trans Pattern Anal Mach Intell, 1986, 8: 34–43

    Article  Google Scholar 

  36. [Online]. Available: http://bcmi.sjtu.edu.cn/houxiaodi.

Download references

Author information

Authors and Affiliations

  1. Institute of Image Processing and Pattern Recognition, Shanghai Jiaotong University, Shanghai, 200240, China

    ZhiQiang Li, Tao Fang & Hong Huo

Authors
  1. ZhiQiang Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tao Fang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hong Huo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tao Fang.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Li, Z., Fang, T. & Huo, H. A saliency model based on wavelet transform and visual attention. Sci. China Inf. Sci. 53, 738–751 (2010). https://doi.org/10.1007/s11432-010-0055-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11432-010-0055-3

Keywords

Search

Navigation