1 January 2001 Feature combination strategies for saliency-based visual attention systems
Author Affiliations +
J. of Electronic Imaging, 10(1), (2001). doi:10.1117/1.1333677
Abstract
Bottom-up or saliency-based visual attention allows primates to detect nonspecific conspicuous targets in cluttered scenes. A classical metaphor, derived from electrophysiological and psychophysical studies, describes attention as a rapidly shiftable ‘‘spotlight.’’ We use a model that reproduces the attentional scan paths of this spotlight. Simple multi-scale ‘‘feature maps’’ detect local spatial discontinuities in intensity, color, and orientation, and are combined into a unique ‘‘master’’ or ‘‘saliency’’ map. The saliency map is sequentially scanned, in order of decreasing saliency, by the focus of attention. We here study the problem of combining feature maps, from different visual modalities (such as color and orientation), into a unique saliency map. Four combination strategies are compared using three databases of natural color images: (1) Simple normalized summation, (2) linear combination with learned weights, (3) global nonlinear normalization followed by summation, and (4) local nonlinear competition between salient locations followed by summation. Performance was measured as the number of false detections before the most salient target was found. Strategy (1) always yielded poorest performance and (2) best performance, with a threefold to eightfold improvement in time to find a salient target. However, (2) yielded specialized systems with poor generalization. Interestingly, strategy (4) and its simplified, computationally efficient approximation (3) yielded significantly better performance than (1), with up to fourfold improvement, while preserving generality.
Laurent Itti, Christof Koch, "Feature combination strategies for saliency-based visual attention systems," Journal of Electronic Imaging 10(1), (1 January 2001). http://dx.doi.org/10.1117/1.1333677
JOURNAL ARTICLE
9 PAGES


SHARE
KEYWORDS
Visualization

Target detection

Databases

Feature extraction

Image filtering

Image processing

Neurons

RELATED CONTENT

A Look at Optoelectronic Document Processing
Proceedings of SPIE (April 12 1990)
Iso-surface volume rendering
Proceedings of SPIE (June 26 1998)
Brain tumor locating in 3D MR volume using symmetry
Proceedings of SPIE (March 21 2014)
Anomaly clustering in hyperspectral images
Proceedings of SPIE (April 27 2009)

Back to Top