IFT-SLIC: A General Framework for Superpixel Generation Based on Simple Linear Iterative Clustering and Image Foresting Transform

Image representation based on super pixels has become indispensable for improving efficiency in Computer Vision systems. Object recognition, segmentation, depth estimation, and body model estimation are some important problems where super pixels can be applied. However, super pixels can influence the efficacy of the system in positive or negative manner, depending on how well they respect the object boundaries in the image. In this paper, we improve super pixel generation by extending a popular algorithm -- Simple Linear Iterative Clustering (SLIC) -- to consider minimum path costs between pixel and cluster centers rather than their direct distances. This creates a new Image Foresting Transform (IFT) operator that naturally defines super pixels as regions of strongly connected pixels by choice of the most suitable path-cost function for a given application. Non-smooth connectivity functions are also explored in our IFT-SLIC approach leading to improved performance. Experimental results indicate better super pixel extraction using the proposed approach as compared to that of SLIC.

[1]  Umar Mohammed,et al.  Superpixel lattices , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[2]  Daniel P. Huttenlocher,et al.  Efficient Graph-Based Image Segmentation , 2004, International Journal of Computer Vision.

[3]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Andrew Blake,et al.  "GrabCut" , 2004, ACM Trans. Graph..

[5]  Alexandre X. Falcão,et al.  IFT-Watershed from gray-scale marker , 2002, Proceedings. XV Brazilian Symposium on Computer Graphics and Image Processing.

[6]  Alexandre X. Falcão,et al.  Data clustering as an optimum‐path forest problem with applications in image analysis , 2009, Int. J. Imaging Syst. Technol..

[7]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Umar Mohammed,et al.  Scene shape priors for superpixel segmentation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[9]  Jorge Stolfi,et al.  The image foresting transform: theory, algorithms, and applications , 2004 .

[10]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Lucy A. C. Mansilla,et al.  Image Segmentation by Image Foresting Transform with Non-smooth Connectivity Functions , 2013, 2013 XXVI Conference on Graphics, Patterns and Images.

[12]  Lucy A. C. Mansilla,et al.  Image Segmentation by Oriented Image Foresting Transform with Geodesic Star Convexity , 2013, CAIP.

[13]  Lucy A. C. Mansilla,et al.  Oriented Image Foresting Transform Segmentation by Seed Competition , 2014, IEEE Transactions on Image Processing.

[14]  Stefano Soatto,et al.  Class segmentation and object localization with superpixel neighborhoods , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[15]  Jonathan Warrell,et al.  “Lattice Cut” - Constructing superpixels using layer constraints , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[16]  Alexandre X. Falcão,et al.  Interactive volume segmentation with differential image foresting transforms , 2004, IEEE Transactions on Medical Imaging.

[17]  Alexandre Gonçalves Silva,et al.  Efficient computation of new extinction values from extended component tree , 2011, Pattern Recognit. Lett..

[18]  Lucy A. C. Mansilla,et al.  Image segmentation by oriented image foresting transform: Handling ties and colored images , 2013, 2013 18th International Conference on Digital Signal Processing (DSP).

[19]  Sven J. Dickinson,et al.  TurboPixels: Fast Superpixels Using Geometric Flows , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.