Vision and Robotics Seminar
will speak on
Class-based, Top-down Segmentation
In this work we present a novel class-based segmentation method, which is guided by a stored representation of the shape of objects within a general class (such as horse images). The approach is different from bottom-up segmentation methods that primarily use the continuity of grey-level, texture, and bounding contours. We show that the method leads to markedly improved segmentation results and can deal with significant variation in shape and varying backgrounds. We discuss the relative merits of class-specific and general image-based segmentation methods and suggest how they can be usefully combined.
This is a joint work with Prof. Shimon Ullman.
The lecture will take place in the
Lecture Hall, Room 1, Ziskind Building
on Thursday, January 3, 2002