Hierarchy and Adaptivity in Segmenting Visual Scenes
Speaker: Eitan Sharon , Division of Applied Mathematics, Brown University
Date: February 18 2004
Time: 2:00PM to 3:00PM
Location: open area of Vision Lab, 6th floor, 400 Tech Sq
Host: Gregory Shakhnarovich, CSAIL
Contact: Gregory Shakhnarovich, gregory@ai.mit.edu
Relevant URL: Abstract:
Image segmentation is one of the most basic tasks for both computer and biological vision systems, and is a prerequisite for higher-level processes from motion detection to object recognition. Segmentation is difficult because objects may differ from their background by any of a variety of properties that can be observed in some, but often not all scales. A further complication is that coarse measurements, for detecting these properties, cannot be obtained by simple geometric averaging, because they often average over properties of neighboring segments, making it difficult to identify the segments and to reliably detect their boundaries. I will present a novel method for segmentation, Segmentation by Weighted Aggregation (SWA). This algorithm efficiently detects segments that optimize a normalized-cut-like measure. The algorithm consists of an adaptive process in which pixels are recursively aggregated into increasingly large-scale aggregates of coherent properties: intensity, texture and boundary integrity. This allows us to detect regions separated by weak, yet consistent edges. The runtime complexity of the algorithm is linear in the number of pixels in the image, and the number of operations per pixel is very low. Numerous experimental results demonstrate a dramatic improvement over current state-of-the-art methods. In addition, the algorithm produces a novel description of the image as a hierarchy of segments.
This is a joint work with Meirav Galun, Ronen Basri and Achi Brandt
See other events that are part of MIT Machine Vision Colloquium Spring 2004
See other events happening in February 2004
