Superpixels and Polygons Using Simple Non-iterative Clustering
2017pp. 4895–4904
Citations Over TimeTop 10% of 2017 papers
Abstract
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.
Related Papers
- → Fundamental relations in simple and 0-simple semihypergroups of small size(2012)8 cited
- → New Characterizations of Simple Points, Minimal Non-simple Sets and P-Simple Points in 2D, 3D and 4D Discrete Spaces(2008)6 cited
- The [0-Simple] Simple Subsemigroups of Nonnegative Matrices(2000)
- → Book Review: IV. Pastorial — Practical Studies: Simple Sermons for Times like These, Simple Sermons on Evangelistic Themes, Simple Talks for Christian Workers, Simple Sermons on Prophetic Themes, Simple Sermons about Jesus Christ, Simple Sermons on Heaven, Hell, and Judgment, Simple Sermons on the Ten Commandments, Simple Sermons for a Sinful Age, Simple Sermons on the Seven Churches of Revelation(1975)