Issue No. 12 - December (2009 vol. 31)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2009.96
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
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.
Superpixels, image segmentation, image labeling, perceptual grouping.
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.