科学计算|超像素分割图像处理|算法

Share Print SLIC Superpixels Abstract
Superpixels are becoming increasingly popular for use in computer vision applications. However, there are few algorithms that output a desired number of regular, compact superpixels with a low computational overhead. We introduce a novel algorithm called SLIC (Simple Linear Iterative Clustering) that clusters pixels in the combined five-dimensional color and image plane space to efficiently generate compact, nearly uniform superpixels. The simplicity of our approach makes it extremely easy to use - a lone parameter specifies the number of superpixels - and the efficiency of the algorithm makes it very practical. Experiments show that our approach produces superpixels at a lower computational cost while achieving a segmentation quality equal to or greater than four state-of-the-art methods, as measured by boundary recall and under-segmentation error. We also demonstrate the benefits of our superpixel approach in contrast to existing methods for two tasks in which superpixels have already been shown to increase performance over pixel-based methods.
Reference
Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Süsstrunk,SLIC Superpixels, EPFL Technical Report no. 149300, June 2010.
Download Windows executable (GUI) Windows GUI based executable
Download Windows executable (Command line) Windows command line based executable
Download 32 bits Linux executable Linux executable (32 bits)
Download 64 bits Linux executable Linux executable (64 bits)
The C++ source code for SLIC superpixels and supervoxels available here: MS Visual Studio 2008 workspace
Sample segmentation output

[Click on the images to see bigger versions.] Visual Comparison with other algorithms



[GS04] Graph-based segmentation	[NC05] Normalized cuts	[TP09] Turbopixels	[QS09] QuickShift	SLIC

Other superpixel methods
[GS04] Felzenszwalb, P., Huttenlocher, D.: Efficient graph-based image segmentation. IJCV (2004).
[NC05] G. Mori, Guiding Model Search Using Segmentation. ICCV (2005).
[TP09] Levinshtein, A., Stere, A., Kutulakos, K., Fleet, D., Dickinson, S., Siddiqi, K.:Turbopixels: Fast superpixels using geometric flows. PAMI (2009)
[QS09] Vedaldi, A., Soatto, S.: Quick shift and kernel methods for mode seeking. ECCV (2008)
Work that uses SLIC superpixels
A. Lucchi, K. Smith, R. Achanta, V. Lepetit and P. Fua,A Fully Automated Approach to Segmentation of Irregularly Shaped Cellular Structures in EM Images, International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), Beijing, China, 2010.

Current research
- Saliency
- Color
- Near Infrared
- Superpixel segmentation
- HDR CFA Image Rendering
- Inpainting
Past research topics
Software & Demos
Downloads

RESEARCH Research projects Join the team Latest publications	TEACHING Courses Projects
LINKS People Jobs & Internships Publications Intranet	MATERIAL Downloads Software Links

Mission
The Images and Visual Representation Group (IVRG) performs research that is primarily focused on the capture, analysis, and reproduction of color images. Aiming to improve everyone's photographic experience, we develop algorithms and systems that help us understand, process, and measure images. Our research areas are computational photography, color image processing, computer vision, and image quality.
CONTACT
Images and Visual Representation Group (IVRG) 【科学计算|超像素分割】 EPFL-IC-IVRG
Station 14
CH-1015 Lausanne
Show on campus map
How to come to EPFL
Tel: +41 (0) 21 693 56 34
Fax: +41 (0) 21 693 43 12