Advertisement

Detecting Perceptually Important Regions in an Image Based on Human Visual Attention Characteristic

  • Kyungjoo Cheoi
  • Yillbyung Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2396)

Abstract

In this paper a new method of automatically detecting perceptually important regions in an image is described. The method uses bottom-up components of human visual attention, and includes the following three components: i) several feature maps known to influence human visual attention, which are computed in parallel directly from the original input image, ii) importance maps, each of which has the measure of “perceptual importance” of local regions of pixels in each corresponding feature map, and are computed based on lateral inhibition scheme, iii) single saliency map, integrated across multiple importance maps based on a simple iterative non-linear mechanism which uses statistical information and local competence of pixels in importance maps. The performance of the system was evaluated over some synthetic and complex real images. Experimental results indicate that our method correlates well with human perception of visually important regions.

Keywords

Input Image Noisy Image Salient Region Computer Vision System Chromatic Information 
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.

References

  1. 1.
    Aguilar, M., Ross, W.: Incremental art:A neural network system for recognition by incremental feature extraction. Proc. of WCNN-93 (1993)Google Scholar
  2. 2.
    Cave, K., Wolfe, J.: Modeling the Role of Parallel Processing in Visual Search. Cognitive Psychology 22 (1990) 225–271CrossRefGoogle Scholar
  3. 3.
    Chapman, D.: Vision, Instruction, and Action. Ph.D. Thesis, AI Laboratory, Massachusetts Institute of Technology (1990)Google Scholar
  4. 4.
    Colby:The neuroanatomy and neurophysiology of attention. Journal of Child Neurology 6 (1991) 90–118Google Scholar
  5. 5.
    Exel, S., Pessoa, L.:Attentive visual recognition. Proc. of Intl. Conf. on Pattern Recognition 1 (1998) 690–692Google Scholar
  6. 6.
    Itti, L., Koch, C., Niebur, E.: Model of saliency-based visual attention for rapid scene analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence (1998) 1254–1259Google Scholar
  7. 7.
    Koch, C., Ullman, S.: Shifts in Selective Visual Attention: Towards the Underlying Neural Circuitry. Human Neurobiology 4 (1985) 219–227Google Scholar
  8. 8.
    Laar, P., Heskes, T., Gielen, S.:Task-Dependent Learning of Attention. Neural Networks 10,6 (1997) 981–992CrossRefGoogle Scholar
  9. 9.
    Milanese, R., Wechsler, H., Gil, S., Bost, J., Pun, T.: Integration of Bottom-up and Top-down Cues for Visual Attention Using Non-Linear Relaxation. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (1994) 781–785Google Scholar
  10. 10.
    Olivier, S., Yasuo, K., Gordon, C.:Development of a Biologically Inspired Real-Time Visual Attention System. In:Lee, S.-W., Buelthoff, H.-H., Poggio, T.(eds.):BMCV 2000.Lecture Notes in Computer Science, Vol. 1811. Springer-Verlag, Berlin Heidelberg New York (2000) 150–159Google Scholar
  11. 11.
    Olshausen, B., Essen, D., Anderson, C.: A neurobiological model of visual attention and Invariant pattern recognition based on dynamic routing of information. NeuroScience 13 (1993) 4700–4719Google Scholar
  12. 12.
    Stewart, B., Reading, I., Thomson, M., Wan, C., Binnie, T.: Directing attention for traffic scene analysis. Proc. of Intl. Conf. on Image Processing and Its Applications (1995) 801–805Google Scholar
  13. 13.
    Treisman, A.-M., Gelade, G.-A.: A Feature-integration Theory of Attention. Cognitive Psychology 12 (1980) 97–136CrossRefGoogle Scholar
  14. 14.
    Yagi, T., Asano, N., Makita, S., Uchikawa, Y.:Active vision inspired by mammalian fixation mechanism. Intelligent Robots and Systems (1995) 39–47Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Kyungjoo Cheoi
    • 1
  • Yillbyung Lee
    • 1
  1. 1.Dept. of Computer ScienceYonsei UniversitySeoulKorea

Personalised recommendations