2009年3月27日星期五

Hierarchy and adaptivity in segmenting visual scenes


Eitan Sharon1, Meirav Galun1, Dahlia Sharon2, Ronen Basri1 & Achi Brandt1

  1. Department of Computer Science and Applied Mathematics, The Weizmann Institute of Science, Rehovot 76100, Israel
  2. Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, Massachusetts 02129, USA
Top of page

Abstract

Finding salient, coherent regions in images is the basis for many visual tasks, and is especially important for object recognition. Human observers perform this task with ease, relying on a system in which hierarchical processing seems to have a critical role1. Despite many attempts, computerized algorithms2, 3, 4, 5 have so far not demonstrated robust segmentation capabilities under general viewing conditions. Here we describe a new, highly efficient approach that determines all salient regions of an image and builds them into a hierarchical structure. Our algorithm, segmentation by weighted aggregation, is derived from algebraic multigrid solvers for physical systems6, and consists of fine-to-coarse pixel aggregation. Aggregates of various sizes, which may or may not overlap, are revealed as salient, without predetermining their number or scale. Results using this algorithm are markedly more accurate and significantly faster (linear in data size) than previous approaches.

没有评论:

发表评论