MAPS: Multiscale attention-based presegmentation of color images. (English) Zbl 1067.68759
Griffin, Lewis D. (ed.) et al., Scale space methods in computer vision. 4th international conference, Scale Space 2003, Isle of Skye, UK, June 10–12, 2003. Proceedings. Berlin: Springer (ISBN 3-540-40368-X/pbk). Lect. Notes Comput. Sci. 2695, 537-549 (2003).
Summary: This paper reports a novel Multiscale Attention-based PreSegmentation method (MAPS) which is built around the multi-feature, multiscale, saliency-based model of visual attention. From the saliency map, provided by the attention algorithm, MAPS first derives the spatial locations of salient regions that will be considered further in the segmentation process. Then, the salient scale and the salient feature of each salient region is determined by exploring the scale and feature spaces computed by the model of attention. A first and rough multiscale segmentation of the salient regions is performed on the corresponding salient scale. This innovative presegmentation but yet uncomplete procedure is followed by some refined segmentation that operates in the salient feature at full resolution.
For the entire collection see [Zbl 1031.68003].
For the entire collection see [Zbl 1031.68003].
MSC:
| 68T45 | Machine vision and scene understanding |
