Color Spectrum Normalization: Saliency Detection Based on Energy Re-allocation

  • Zhuoliang Kang
  • Junping Zhang
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6297)


Spectrum normalization is a process shared by two saliency detection methods, Spectral Residual (SR) and Phase Fourier Transform (PFT). In this paper, we point out that the essence of spectrum normalization is the re-allocation of energy. By re-allocating normalized energy in particular frequency region to the whole background, the salient objects are effectively highlighted and the energy of the background is weakened. Considering energy distribution in both spectral domain and color channels, we propose a simple and effective visual saliency model based on Energy Re-allocation mechanism (ER). We combine color energy normalization, spectrum normalization and channel energy normalization to attain an energy re-allocation map. Then, we convert the map to the corresponding saliency map using a low-pass filter. Compared with other state-of-the-art models, experiments on both natural images and psychological images indicate that ER can better detect the salient objects with a competitive computational speed.


Natural Image Color Channel Salient Object Spectrum Normalization Saliency Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hou, X., Zhang, L.: Dynamic Visual Attention: Searching for Coding Length Increments. In: NIPS, vol. 20 (2008)Google Scholar
  2. 2.
    Wang, Y.S., Tai, C.W., Sorkine, O., Lee, T.Y.: Optimized Scale-and-Stretch for Image Resizing. SIGGRAPH ASIA (2008)Google Scholar
  3. 3.
    Itti, L., Koch, C., Niebur, E.: A model of Saliency-based Visual Attention for Rapid Scene Analysis. TPAMI 20, 1254–1259 (1998)Google Scholar
  4. 4.
    Bruce, N., Tsotsos, J.: Saliency Based on Information Maximization. In: NIPS, vol. 18 (2006)Google Scholar
  5. 5.
    Gao, D., Vasconcelos, N.: Bottom-up Saliency is A Discriminant Process. In: ICCV (2007)Google Scholar
  6. 6.
    Gao, D., Vasconcelos, N.: An Experimental Comparison of Three Guiding Principles for The Detection Salient Image Locations: Stability, Complexity, and Discrimination. In: CVPR workshops (2005)Google Scholar
  7. 7.
    Lowe, D.G.: Object Recognition from Local Scale-invariant Features. In: ICCV (1999)Google Scholar
  8. 8.
    Sebe, N., Lew, M.S.: Comparing Salient Point Detectors. In: ICME (2001)Google Scholar
  9. 9.
    Kadir, T., Brady, M.I.: Scale, Saliency and Image Description. IJCV 45, 83–105 (2001)zbMATHCrossRefGoogle Scholar
  10. 10.
    Achanta, R., Hemami, S., Estrada, F., Süsstrunk, S.: Frequency-tuned Salient Region Detection. In: CVPR (2009)Google Scholar
  11. 11.
    Hou, X., Zhang, L.: Saliency Detection: A Spectral Residual Approach. In: CVPR (2007)Google Scholar
  12. 12.
    Guo, C., Ma, Q., Zhang, L.: Spatio-temporal Saliency Detection Using Phase Spectrum of Quaternion Fourier Transform. In: CVPR (2008)Google Scholar
  13. 13.
    Field, D.J.: Relations Between the Statistics of Natural Images and The Response Properties of Cortical Cells. JOSA A 4, 2379–2394 (1987)CrossRefGoogle Scholar
  14. 14.
    Field, D.J.: What is the Goal of Sensory Coding? Source Neural Computation archive 6, 559–601 (1994)Google Scholar
  15. 15.
    He, D.-C., Wang, L.: Texture Unit, Texture Spectrum, and Texture Analysis. TGRS 28, 509–512 (1990)Google Scholar
  16. 16.
    Oppenheim, A.V., Lim, J.S.: The Importance of Phase in Signals. Proceedings of the IEEE 69, 529–541 (1981)CrossRefGoogle Scholar
  17. 17.
    Wolfe, J.M.: Asymmetries in Visual Search: An Introduction. Perception and psychophysics 63, 381–389 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Zhuoliang Kang
    • 1
  • Junping Zhang
    • 2
  1. 1.Department of Communication Science and EngineeringFudan UniversityShanghaiChina
  2. 2.Shanghai Key Lab of Intelligent Information Processing, School of Computer ScienceFudan UniversityShanghaiChina

Personalised recommendations