The Community for Technology Leaders
Green Image
Issue No. 11 - Nov. (2012 vol. 34)
ISSN: 0162-8828
pp: 2274-2282
Sabine Süsstrunk , Images & Visual Representation Group, Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland
P. Fua , Comput. Vision Lab., Polytech. Fed. de Lausanne, Lausanne, Switzerland
A. Shaji , Images & Visual Representation Group, Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland
A. Lucchi , Comput. Vision Lab., Polytech. Fed. de Lausanne, Lausanne, Switzerland
K. Smith , Zurich Light Microscopy Center, ETH Zurich, Zurich, Switzerland
R. Achanta , Images & Visual Representation Group, Ecole Polytech. Fed. de Lausanne, Lausanne, Switzerland
ABSTRACT
Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks of existing methods, we empirically compare five state-of-the-art superpixel algorithms for their ability to adhere to image boundaries, speed, memory efficiency, and their impact on segmentation performance. We then introduce a new superpixel algorithm, simple linear iterative clustering (SLIC), which adapts a k-means clustering approach to efficiently generate superpixels. Despite its simplicity, SLIC adheres to boundaries as well as or better than previous methods. At the same time, it is faster and more memory efficient, improves segmentation performance, and is straightforward to extend to supervoxel generation.
INDEX TERMS
Clustering algorithms, Image segmentation, Complexity theory, Image color analysis, Image edge detection, Measurement uncertainty, Approximation algorithms, k-means, Superpixels, segmentation, clustering
CITATION
Sabine Süsstrunk, P. Fua, A. Shaji, A. Lucchi, K. Smith, R. Achanta, "SLIC Superpixels Compared to State-of-the-Art Superpixel Methods", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 34, no. , pp. 2274-2282, Nov. 2012, doi:10.1109/TPAMI.2012.120
102 ms
(Ver 3.3 (11022016))