An Integrated Saliency Model with Guidance of Eye Movement in Natural Scene Classification

Abstract:

Nature Scene classification is a fundamental problem in image understanding. Human can recognize the scene instantly after only a glance. This is mainly because that our visual attention is easily attracted by the salient objects in scene. And these objects are always representative in the natural scene. It is unclear how humans achieve rapid scene categorization. But this kind of high-level cognitive behavior can be reflected by the eye movement. To identify this ability, we propose a model with the guidance of eye movement. It combines the bag of words (BOW) and spatial pyramid matching (SPM) methods to train and test our model on support vector machine (SVM). The eye movement experiments were employed to validate our model. We found that the subjects could recognize the scenes correctly even if given only a few saliency patches with less than one second. These results suggest that the eye tracking saliency patches play an important role for human scene categorization.

• Periodical: Applied Mechanics and Materials (Volume 678)
• Pages: 147-150
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.678.147
• Online since: October 2014
• Authors: Yu Liang Du*, Ling Feng Yuan, Wei Bing Wan
• Keywords: Bag of Words, Eye Movement, Saliency, Scene Classification, Spatial Pyramid Matching

References

[1] Henderson, John M., and Andrew Hollingworth: Annual review of psychology 50. 1 (1999): 243-271.

[2] Benmokhtar, Rachid, Benoit Huet, and S-A. Berrani. Low-level feature fusion models for soccer scene classification., Multimedia and Expo, 2008 IEEE International Conference on. IEEE, (2008).

DOI: 10.1109/icme.2008.4607688

[3] Fei-Fei, Li, and Pietro Perona. A bayesian hierarchical model for learning natural scene categories., Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on. Vol. 2. IEEE, (2005).

DOI: 10.1109/cvpr.2005.16

[4] Greene, Michelle R: Frontiers in psychology 4 (2013).

[5] Wolfe, Jeremy M., et al.: Trends in cognitive sciences 15. 2 (2011): 77-84.

[6] Schütz, Alexander C., Doris I. Braun, and Karl R. Gegenfurtner: Journal of vision 11. 5 (2011): 9.

[7] Simoncelli, Eero P., and William T. Freeman. The steerable pyramid: A flexible architecture for multi-scale derivative computation., Image Processing, International Conference on. Vol. 3. IEEE Computer Society, (1995).

DOI: 10.1109/icip.1995.537667

[8] Torralba, Antonio, et al.: Psychological review 113. 4 (2006): 766.

[9] Lazebnik, Svetlana, Cordelia Schmid, and Jean Ponce. Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories., Computer Vision and Pattern Recognition, 2006 IEEE Computer Society Conference on. Vol. 2. IEEE, (2006).

DOI: 10.1109/cvpr.2006.68