The Community for Technology Leaders
Green Image
Issue No. 12 - December (2009 vol. 31)
ISSN: 0162-8828
pp: 2290-2297
Alex Levinshtein , University of Toronto, Toronto
Adrian Stere , University of Toronto, Toronto
Kiriakos N. Kutulakos , University of Toronto, Toronto
David J. Fleet , University of Toronto, Toronto
Sven J. Dickinson , University of Toronto, Toronto
Kaleem Siddiqi , McGill University, Montreal
ABSTRACT
We describe a geometric-flow-based algorithm for computing a dense oversegmentation of an image, often referred to as superpixels. It produces segments that, on one hand, respect local image boundaries, while, on the other hand, limiting undersegmentation through a compactness constraint. It is very fast, with complexity that is approximately linear in image size, and can be applied to megapixel sized images with high superpixel densities in a matter of minutes. We show qualitative demonstrations of high-quality results on several complex images. The Berkeley database is used to quantitatively compare its performance to a number of oversegmentation algorithms, showing that it yields less undersegmentation than algorithms that lack a compactness constraint while offering a significant speedup over N-cuts, which does enforce compactness.
INDEX TERMS
Superpixels, image segmentation, image labeling, perceptual grouping.
CITATION

A. Levinshtein, K. Siddiqi, D. J. Fleet, S. J. Dickinson, K. N. Kutulakos and A. Stere, "TurboPixels: Fast Superpixels Using Geometric Flows," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 31, no. , pp. 2290-2297, 2009.
doi:10.1109/TPAMI.2009.96
94 ms
(Ver 3.3 (11022016))