@INPROCEEDINGS{Coup1208:Multi,
AUTHOR="Camille Couprie",
TITLE="Multi-label Energy Minimization for Object Class Segmentation",
BOOKTITLE="20th European Signal Processing Conference 2012 (EUSIPCO 2012)",
ADDRESS="Bucharest, Romania",
DAYS=27,
MONTH=aug,
YEAR=2012,
KEYWORDS="Image processing; Object class segmentation; Graph-based optimization;
Graph cuts; Watershed; Random walker",
ABSTRACT="The task of associating a semantic class to the objects present in an image
is challenging because this problem involves the joint segmentation and
recognition of the objects. In this work, we use a recent approach
embedding several optimization algorithms into a common framework named
Power watershed to perform this task. We show how the fast watershed
algorithm can be used to minimize an energy function for which the
minimizer corresponds to the desired object class segmentation. Higher
order potentials are then added to improve label consistency. We also
demonstrate that the random walker algorithm can be successfully applied to
semantic class segmentation problems. Comparisons with the Graph Cuts
algorithm show that the proposed approaches yield better segmentation
results, obtained up to twelve times faster on a very challenging indoor
scenes dataset."
}