Skip to main content

Research Repository

Advanced Search

SMURFS: superpixels from multi-scale refinement of super-regions

Luengo, Imanol; Basham, Mark; French, Andrew P.

Authors

Imanol Luengo psxil1@nottingham.ac.uk

Mark Basham



Abstract

Recent applications in computer vision have come to rely on superpixel segmentation as a pre-processing step for higher level vision tasks, such as object recognition, scene labelling or image segmentation. Here, we present a new algorithm, Superpixels from MUlti-scale ReFinement of Super-regions (SMURFS), which not only obtains state-of-the-art superpixels, but can also be applied hierarchically to form what we call n-th order super-regions. In essence, starting from a uniformly distributed set of super-regions, the algorithm iteratively alternates graph-based split and merge optimization schemes which yield superpixels that better represent the image. The split step is performed over the pixel grid to separate large super-regions into different smaller superpixels. The merging process, conversely, is performed over the superpixel graph to create 2nd-order super-regions (super-segments). Iterative refinement over two scale of regions allows the algorithm to achieve better over-segmentation results than current state-of-the-art methods, as experimental results show on the public Berkeley Segmentation Dataset (BSD500).

Citation

Luengo, I., Basham, M., & French, A. P. (2016). SMURFS: superpixels from multi-scale refinement of super-regions

Conference Name British Machine Vision Conference (BMVC 2016)
End Date Sep 22, 2016
Acceptance Date Jul 14, 2016
Publication Date Sep 20, 2016
Deposit Date Sep 21, 2016
Publicly Available Date Sep 21, 2016
Peer Reviewed Peer Reviewed
Keywords Segmentation, Super pixels
Public URL http://eprints.nottingham.ac.uk/id/eprint/37025
Publisher URL http://www.bmva.org/bmvc/2016/papers/paper004/index.html
Related Public URLs http://www.bmva.org/bmvc/2016/toc.html
Copyright Statement Copyright information regarding this work can be found at the following address: http://eprints.nottingham.ac.uk/end_user_agreement.pdf

Files


paper004.pdf (10 Mb)
PDF

Copyright Statement
Copyright information regarding this work can be found at the following address: http://eprints.nottingham.ac.uk/end_user_agreement.pdf





You might also like



Downloadable Citations