Superpixels and Polygons Using Simple Non-iterative Clustering

We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we als...

Full description

Saved in:
Bibliographic Details
Published in2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4895 - 4904
Main Authors Achanta, Radhakrishna, Susstrunk, Sabine
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2017
Subjects
Clustering algorithms
Estimation
Image color analysis
Image segmentation
Iterative algorithms
Memory management
Partitioning algorithms
Online AccessGet full text
ISSN1063-6919
1063-6919
DOI10.1109/CVPR.2017.520

Cover

More Information
Summary:We present an improved version of the Simple Linear Iterative Clustering (SLIC) superpixel segmentation. Unlike SLIC, our algorithm is non-iterative, enforces connectivity from the start, requires lesser memory, and is faster. Relying on the superpixel boundaries obtained using our algorithm, we also present a polygonal partitioning algorithm. We demonstrate that our superpixels as well as the polygonal partitioning are superior to the respective state-of-the-art algorithms on quantitative benchmarks.
ISSN:1063-6919
1063-6919
DOI:10.1109/CVPR.2017.520