Image Segmentation by Cascaded Region Agglomeration

We propose a hierarchical segmentation algorithm that starts with a very fine over segmentation and gradually merges regions using a cascade of boundary classifiers. This approach allows the weights of region and boundary features to adapt to the segmentation scale at which they are applied. The sta...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE Conference on Computer Vision and Pattern Recognition pp. 2011 - 2018
Main Authors Zhile Ren, Shakhnarovich, Gregory
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2013
Subjects
boundary detection
cascade
edge detection
Image color analysis
Image segmentation
Logistics
Merging
Partitioning algorithms
Shape
superpixels
Training
Online AccessGet full text

Cover

More Information
Summary:We propose a hierarchical segmentation algorithm that starts with a very fine over segmentation and gradually merges regions using a cascade of boundary classifiers. This approach allows the weights of region and boundary features to adapt to the segmentation scale at which they are applied. The stages of the cascade are trained sequentially, with asymetric loss to maximize boundary recall. On six segmentation data sets, our algorithm achieves best performance under most region-quality measures, and does it with fewer segments than the prior work. Our algorithm is also highly competitive in a dense over segmentation (super pixel) regime under boundary-based measures.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2013.262