Image and Video Saliency Models Improvement by Blur Identification

  • Yoann Baveye
  • Fabrice Urban
  • Christel Chamaret
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7594)


Visual saliency models aim at predicting where people look. In free viewing conditions, people look at relevant objects that are in focus. Assuming blurred or out-of-focus objects do not belong to the region of interest, this paper proposes a significant improvement and the validation of a saliency model by taking blur into account. Blur identification is associated to a spatio-temporal saliency model. Bottom-up models are designed to mimic the low-level processing of the human visual system and can thus detect out-of-focus objects as salient. The blur identification allows decreasing saliency values on blurred areas while increasing values on sharp areas. In order to validate our new saliency model we conducted eye-tracking experiments to record ground truth of observer’s fixations on images and videos. Blur identification significantly improves fixation prediction for natural images and videos.


Visual attention Saliency Blur image processing 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Khan, R.A., Konik, H., Dinet, E.: Enhanced image saliency model based on blur identification. In: 25th International Conference of IVCNZ (December 2010)Google Scholar
  2. 2.
    Le Meur, O., Le Callet, P., Barba, D.: Predicting visual fixations on video based on low-level visual features. Vision Res. 47(19), 2483–2498 (2007)CrossRefGoogle Scholar
  3. 3.
    Itti, L., Koch, C., Niebur, E.: Model of saliency-based visual attention for rapid scene analysis. IEEE PAMI 20, 1254–1259 (1998)CrossRefGoogle Scholar
  4. 4.
    Daly, S.: The visible differences predictor: An algorithm of image fidelity. In: Digital Images and Human Vision, pp. 179–206 (1993)Google Scholar
  5. 5.
    Mannos, J.L., Sakrison, D.J.: The effects of a visual fidelity criterion on the encoding of images. IEEE TIT 20(4), 525–536 (1974)zbMATHGoogle Scholar
  6. 6.
    Urban, F., Follet, B., Chamaret, C., Le Meur, O., Baccino, T.: Medium Spatial Frequencies, a Strong Predictor of Salience. Cogn. Comput. 3, 37–47 (2011)CrossRefGoogle Scholar
  7. 7.
    Le Meur, O., Thoreau, D., Le Callet, P., Barba, D.: A spatio-temporal model of the selective human visual attention. In: IEEE ICIP, vol. 3, pp. 1188–1191 (2005)Google Scholar
  8. 8.
    Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Hum Neurobiol. 4, 219–227 (1985)Google Scholar
  9. 9.
    Tong, H.: Blur detection for digital images using wavelet transform. In: Proceedings of IEEE ICME, pp. 17–20 (2004)Google Scholar
  10. 10.
    Urban, F., Nezan, J.F., Raulet, M.: HDS, a real-time multi-DSP motion estimator for MPEG-4 H.264 AVC high definition video encoding. Springer Journal of Real-Time Image Processing 4, 23–31 (2009)CrossRefGoogle Scholar
  11. 11.
    Peters, R., Iyer, A., Itti, L., Koch, C.: Components of bottom-up gaze allocation in natural images. Vision Research 45, 2397–2416 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Yoann Baveye
    • 1
  • Fabrice Urban
    • 1
  • Christel Chamaret
    • 1
  1. 1.TechnicolorCesson SevigneFrance

Personalised recommendations