A Method of Extracting Objects of Interest with Possible Broad Application in Computer Vision

  • Kyungjoo Cheoi
  • Yillbyung Lee
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2525)


An approach of using a biologically motivated attention system to extracting objects of interest from an image is presented with possible broad application in computer vision. Starting with an RGB image, four streams of biologically motivated features are extracted and reorganized in order to calculate a saliency map allowing the selection of the most interesting objects. The approach is tested on three different types of images showing reasonable results. In addition, in order to verify the results on real images, we performed human test and compared the measured behaviors of human subjects with the results of the system.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Burt, P.J.:Attention mechanisms for vision in a dynamic world. Proc. of Intl. Conf. on Pattern Recognition 2 (1998) 977–987Google 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.
    Exel, S., Pessoa, L.:Attentive visual recognition. Proc. of Intl. Conf. on Pattern Recognition 1 (1998) 690–692Google Scholar
  4. 4.
    Koch, C., Ullman, S.: Shifts in Selective Visual Attention: Towards the Underlying Neural Circuitry. Human Neurobiology 4 (1985) 219–227Google Scholar
  5. 5.
    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
  6. 6.
    Itti, L., Koch, C.,: A saliency-based search mechanism for overt and covert shifts of visual attention. Vision Research 40 (2000) 1489–1506CrossRefGoogle Scholar
  7. 7.
    Itti. L, Koch. C.: A comparison of feature combination strategies for saliency-based visual attention systems. In Proc. SPIE Human Vision and Electronic Imaging IV 3644 (2000) 1473–1506Google Scholar
  8. 8.
    Itti. L, Koch. C.: Computational modeling visual attention. Nature Neuroscience Review. 2 (2001) 194–204CrossRefGoogle Scholar
  9. 9.
    Laar, P., Heskes, T., Gielen, S.:Task-Dependent Learning of Attention. Neural Networks 10, 6 (1997) 981–992CrossRefGoogle Scholar
  10. 10.
    Milanese, R., Bost, J., Pun, Thierry.: A Bottom-up Attention system For Active Vision. Proc. of 10th European Conf. on Artificial Intelligence (1992)Google Scholar
  11. 11.
    Milanese, R., Wechsler, H., Gil, S., Bost, J., Pun, T.: Integration of Bottom-up and Topdown Cues for Visual Attention Using Non-Linear Relaxation. Proc. of IEEE Conf. on Computer Vision and Pattern Recognition (1994) 781–785Google Scholar
  12. 12.
    Mozer, M.: The Perception of Multiple Objects: a Connectionist Approach. MIT Press, Cambridge, MA (1991)Google Scholar
  13. 13.
    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
  14. 14.
    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
  15. 15.
    Parasuraman. R.,:The attentive brain. MIT Press, Cambridge, MA, (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Kyungjoo Cheoi
    • 1
  • Yillbyung Lee
    • 2
  1. 1.Information Technology Group Division R&D CenterLG CNS Co., Ltd.SeoulKorea
  2. 2.Dept. of Computer Science and Industrial Systems EngineeringYonsei UniversitySeoulKorea

Personalised recommendations