A Comparison of Feature Detectors with Passive and Task-Based Visual Saliency
This paper investigates the coincidence between six interest point detection methods (SIFT, MSER, Harris-Laplace, SURF, FAST & Kadir-Brady Saliency) with two robust “bottom-up” models of visual saliency (Itti and Harel) as well as “task” salient surfaces derived from observer eye-tracking data. Comprehensive statistics for all detectors vs. saliency models are presented in the presence and absence of a visual search task. It is found that SURF interest-points generate the highest coincidence with saliency and the overlap is superior by 15% for the SURF detector compared to other features. The overlap of image features with task saliency is found to be also distributed towards the salient regions. However the introduction of a specific search task creates high ambiguity in knowing how attention is shifted. It is found that the Kadir-Brady interest point is more resilient to this shift but is the least coincident overall.
- 2.Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline sterio from maximally stable extremal regions. In: Proc. of British Machine Vision Conference, pp. 384-393 (2002) Google Scholar
- 5.Rosten, E., Drummond, T.: Fusing points and lines for high performance tracking. In: 10th IEEE International Conference on Computer Vision, vol. 2, pp. 1508–1511 (2005)Google Scholar
- 10.Gao, K., Lin, S., Zhang, Y., Tang, S., Ren, H.: Attention Model Based SIFT Keypoints Filtration for Image Retrieval. In: Proc. ICIS 2008, pp. 191–196 (2008)Google Scholar
- 12.Harel, J., Koch, C., Perona, P.: Graph-Based Visual Saliency. In: Advances in Neural Information Processing Systems, vol. 19, pp. 545–552 (2006)Google Scholar
- 15.Peters, R.J., Itti, L.: Beyond bottom-up: Incorporating task-dependent influences into a computational model of spatial attention. In: Proc. IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)Google Scholar