Notice
This item was automatically migrated from a legacy system. It's data has not been checked and might not meet the quality criteria of the present system.
Haxhimusa, Y. (2012). Interactive Labeling of Image Segmentation Hierarchies. In Statistische Woche (pp. 71–72). http://hdl.handle.net/20.500.12708/54307
E193-03 - Forschungsbereich Pattern Recognition and Image Processing
-
Published in:
Statistische Woche
-
Date (published):
2012
-
Event name:
Statistische Woche 2012
-
Event date:
18-Sep-2012 - 21-Sep-2012
-
Event place:
TU Wien, Austria
-
Number of Pages:
2
-
Peer reviewed:
Yes
-
Abstract:
We study the task of interactive semantic labeling of a given segmentation hierarchy and
present a framework consisting of two parts: an automatic component, based on a Conditional
Random Field whose dependencies are de ned by the inclusion tree of the segmentation
hierarchy, and a feedback-loop provided by a human user. Experiments on two data sets
show higher classi cation rates for the proposed framework than a baseline, that classi es
all segments independently.
en
Research Areas:
Visual Computing and Human-Centered Technology: 100%