will speak on
Multiscale in vision:
image segmentation and boundary detection
using adaptive measurements in multiple levels
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, applied to the image for detecting these properties, 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), which generates and combines multiscale measurements of intensity contrast, texture differences, and boundary integrity. This algorithm efficiently detects segments that optimize a normalized-cut-like measure. The algorithm uses an adaptive process to recursively coarsen a graph that reflects similarities between properties of neighboring regions in the image. Moreover the algorithm produces a novel description of the image as a hierarchy of segments. I will present results demonstrating a dramatic improvement over current state-of-the-art methods.
This is a joint work with Ronen Basri and Achi Brandt.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, February 28, 2002