Shape Guided Object Segmentation

We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible fi...

Full description

Saved in:
Bibliographic Details
Main Authors: Borenstein, E., Malik, J.
Format: Conference Proceeding
Language:English
Subjects:
Approximation algorithms
Bayesian methods
Horses
Image segmentation
Inference algorithms
Labeling
Object detection
Object segmentation
Robustness
Shape
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We construct a Bayesian model that integrates topdown with bottom-up criteria, capitalizing on their relative merits to obtain figure-ground segmentation that is shape-specific and texture invariant. A hierarchy of bottom-up segments in multiple scales is used to construct a prior on all possible figure-ground segmentations of the image. This prior is used by our top-down part to query and detect object parts in the image using stored shape templates. The detected parts are integrated to produce a global approximation for the object's shape, which is then used by an inference algorithm to produce the final segmentation. Experiments with a large sample of horse and runner images demonstrate strong figure-ground segmentation despite high object and background variability. The segmentations are robust to changes in appearance since the matching component depends on shape criteria alone. The model may be useful for additional visual tasks requiring labeling, such as the segmentation of multiple scene objects.
ISSN:1063-6919
DOI:10.1109/CVPR.2006.276