Skip to main content

Multiscale Discriminant Saliency for Visual Attention

  • Conference paper
Computational Science and Its Applications – ICCSA 2013 (ICCSA 2013)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 7971))

Included in the following conference series:

  • 2380 Accesses

Abstract

The bottom-up saliency, an early stage of humans’ visual attention, can be considered as a binary classification problem between center and surround classes. Discriminant power of features for the classification is measured as mutual information between features and two classes distribution. The estimated discrepancy of two feature classes very much depends on considered scale levels; then, multi-scale structure and discriminant power are integrated by employing discrete wavelet features and Hidden markov tree (HMT). With wavelet coefficients and Hidden Markov Tree parameters, quad-tree like label structures are constructed and utilized in maximum a posterior probability (MAP) of hidden class variables at corresponding dyadic sub-squares. Then, saliency value for each dyadic square at each scale level is computed with discriminant power principle and the MAP. Finally, across multiple scales is integrated the final saliency map by an information maximization rule. Both standard quantitative tools such as NSS, LCC, AUC and qualitative assessments are used for evaluating the proposed multiscale discriminant saliency method (MDIS) against the well-know information-based saliency method AIM on its Bruce Database wity eye-tracking data. Simulation results are presented and analyzed to verify the validity of MDIS as well as point out its disadvantages for further research direction.

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

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Abramovich, F., Sapatinas, T., Silverman, B.W.: Wavelet thresholding via a bayesian approach. Journal of the Royal Statistical Society: Series B (Statistical Methodology) 60(4), 725–749 (1998)

    Article  MathSciNet  MATH  Google Scholar 

  2. A\ccık, A., Onat, S., Schumann, F., Einhäuser, W., König, P.: Effects of luminance contrast and its modifications on fixation behavior during free viewing of images from different categories. Vision Research 49(12), 1541 (2009)

    Article  Google Scholar 

  3. Baddeley, R.J., Tatler, B.W.: High frequency edges (but not contrast) predict where we fixate: A bayesian system identification analysis. Vision Research 46(18), 2824–2833 (2006)

    Article  Google Scholar 

  4. Borji, A., Sihite, D.N., Itti, L.: Quantitative analysis of Human-Model agreement in visual saliency modeling: A comparative study. IEEE Transactions on Image Processing (2012)

    Google Scholar 

  5. Bouman, C., Shapiro, M.: A multiscale random field model for bayesian image segmentation. IEEE Transactions on Image Processing 3(2), 162–177 (1994)

    Article  Google Scholar 

  6. Bruce, N., Tsotsos, J.: Saliency based on information maximization. Advances in Neural Information Processing Systems 18, 155 (2006)

    Google Scholar 

  7. Bruce, N.D.B., Loach, D.P., Tsotsos, J.K.: Visual correlates of fixation selection: a look at the spatial frequency domain. In: IEEE International Conference on Image Processing, ICIP 2007, vol. 3, p. III–289 (2007)

    Google Scholar 

  8. Cheng, H., Bouman, C.A., Allebach, J.P.: Multiscale document segmentation 1. In: IS and T Annual Conference, pp. 417–425 (1997)

    Google Scholar 

  9. Cheng, H., Bouman, C.: Trainable context model for multiscale segmentation. In: Proceedings of the 1998 International Conference on Image Processing, ICIP 1998, vol. 1, pp. 610–614 (October 1998)

    Google Scholar 

  10. Chipman, H.A., Kolaczyk, E.D., McCulloch, R.E.: Adaptive bayesian wavelet shrinkage. Journal of the American Statistical Association 92(440), 1413–1421 (1997)

    Article  MATH  Google Scholar 

  11. Choi, H., Baraniuk, R.: Multiscale image segmentation using wavelet-domain hidden markov models. IEEE Transactions on Image Processing 10(9), 1309–1321 (2001)

    Article  MathSciNet  Google Scholar 

  12. Choi, H., Baraniuk, R.: Multiscale texture segmentation using wavelet-domain hidden markov models. In: Conference Record of the Thirty-Second Asilomar Conference on Signals, Systems & Computers, vol. 2, pp. 1692–1697 (November 1998)

    Google Scholar 

  13. Crouse, M., Baraniuk, R.: Simplified wavelet-domain hidden markov models using contexts. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, vol. 4, pp. 2277–2280 (May 1998)

    Google Scholar 

  14. Gao, D., Mahadevan, V., Vasconcelos, N.: The discriminant center-surround hypothesis for bottom-up saliency. Advances in Neural Information Processing Systems 20, 1–8 (2007)

    MATH  Google Scholar 

  15. Gao, D., Mahadevan, V., Vasconcelos, N.: On the plausibility of the discriminant center-surround hypothesis for visual saliency. Journal of Vision 8(7) (2008)

    Google Scholar 

  16. Gao, D., Vasconcelos, N.: Discriminant saliency for visual recognition from cluttered scenes. Advances in Neural Information Processing Systems 17, 481–488 (2004)

    Google Scholar 

  17. Gao, D., Vasconcelos, N.: Discriminant interest points are stable. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–6 (2007)

    Google Scholar 

  18. Gao, D., Vasconcelos, N.: Decision-theoretic saliency: computational principles, biological plausibility, and implications for neurophysiology and psychophysics. Neural Computation 21(1), 239–271 (2009)

    Article  MATH  Google Scholar 

  19. Harel, J., Koch, C., Perona, P.: Graph-based visual saliency. In: NIPS (2007)

    Google Scholar 

  20. Hou, X., Zhang, L.: Saliency detection: A spectral residual approach. In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2007, pp. 1–8 (2007)

    Google Scholar 

  21. Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(11), 1254–1259 (1998)

    Article  Google Scholar 

  22. Le Ngo, A.C., Ang, L.M., Seng, K.P., Qiu, G.: Improvement and evaluation of visual saliency based on information theory. In: 2010 International Computer Symposium (ICS), pp. 500–505 (2010)

    Google Scholar 

  23. Le Ngo, A.C., Qiu, G., Underwood, G., Ang, L.M., Seng, K.P.: Visual saliency based on fast nonparametric multidimensional entropy estimation. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1305–1308 (2012)

    Google Scholar 

  24. Li, J., Gray, R., Olshen, R.: Multiresolution image classification by hierarchical modeling with two-dimensional hidden markov models. IEEE Transactions on Information Theory 46(5), 1826–1841 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  25. Marr, D., Marr, D.: Early processing of visual information. Philosophical Transactions of the Royal Society of London. B, Biological Sciences 275(942), 483–519 (1976)

    Article  Google Scholar 

  26. Neisser, U.: Cognitive psychology. APA (1967)

    Google Scholar 

  27. Parkhurst, D., Law, K., Niebur, E.: Modeling the role of salience in the allocation of overt visual attention. Vision Research 42(1), 107–124 (2002)

    Article  Google Scholar 

  28. Pesquet, J., Krim, H., Leporini, D., Hamman, E.: Bayesian approach to best basis selection. In: 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 1996. Conference Proceedings, vol. 5, pp. 2634–2637 (May 1996)

    Google Scholar 

  29. Qiu, G., Gu, X., Chen, Z., Chen, Q., Wang, C.: An information theoretic model of spatiotemporal visual saliency. In: 2007 IEEE International Conference on Multimedia and Expo., pp. 1806–1809 (July 2007)

    Google Scholar 

  30. Reinagel, P., Zador, A.M.: Natural scene statistics at the centre of gaze. Network: Computation in Neural Systems 10(4), 341–350 (1999)

    Article  MATH  Google Scholar 

  31. Romberg, J., Choi, H., Baraniuk, R.: Bayesian tree-structured image modeling using wavelet-domain hidden markov models. IEEE Transactions on Image Processing 10(7), 1056–1068 (2001)

    Article  Google Scholar 

  32. Sun, Y., Fisher, R.: Object-based visual attention for computer vision. Artificial Intelligence 146(1), 77–123 (2003)

    Article  MathSciNet  MATH  Google Scholar 

  33. Tatler, B.W., Baddeley, R.J., Gilchrist, I.D.: Visual correlates of fixation selection: Effects of scale and time. Vision Research 45(5), 643–659 (2005)

    Article  Google Scholar 

  34. Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cognitive Psychology 12(1), 97–136 (1980)

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2013 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Le Ngo, A.C., Ang, K.LM., Qiu, G., Kah-Phooi, J.S. (2013). Multiscale Discriminant Saliency for Visual Attention. In: Murgante, B., et al. Computational Science and Its Applications – ICCSA 2013. ICCSA 2013. Lecture Notes in Computer Science, vol 7971. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-39637-3_37

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-39637-3_37

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-39636-6

  • Online ISBN: 978-3-642-39637-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics