Improving Scene Recognition through Visual Attention
In this paper we study how the use of a novel model of bottom-up saliency (visual attention), based on local energy and color, can significantly accelerate scene recognition and, at the same time, preserve the recognition performance. To do so, we use a mobile robot-like application where scene recognition is performed through the use of SIFT features to characterize the different scenarios, and the Nearest Neighbor rule to carry out the classification. Experimental work shows that important reductions in the size of the database of prototypes can be achieved (17.6% of the original size) without significant losses in recognition performance (from 98.5% to 96.1%), thus accelerating the classification task.
KeywordsVisual Attention Recognition Performance Database Size Sift Feature Scene Recognition
Unable to display preview. Download preview PDF.
- 2.Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Human Neurobiology 4(4), 219–227 (1985)Google Scholar
- 3.García-Díaz, A., Fdez-Vidal, X.R., Dosil, R., Pardo, X.M.: Local Energy Variability as a Generic Measure of Bottom-Up Salience. In: Yin, P.-Y. (ed.) Pattern Recognition Techniques, Technology and Applications, In-Teh, Vienna, ch. 1, pp. 1–24 (2008)Google Scholar
- 6.Bonaiuto, J.J., Itti, L.: Combining attention and recognition for rapid scene analysis. In: Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005), vol. (III)90, p. 90 (2005)Google Scholar
- 10.Kovesi, P.: Invariant Measures of Image Features from Phase Information. Ph.D. Thesis, The University or Western Australia (1996)Google Scholar