Seeded watershed cut uncertainty estimators for guided interactive segmentation

Watershed cuts are among the fastest segmentation algorithms and therefore well suited for interactive segmentation of very large 3D data sets. To minimize the number of user interactions (“seeds”) required until the result is correct, we want the computer to actively query the human for input at the most critical locations, in analogy to active learning. These locations are found by means of suitable uncertainty measures. We propose various such measures for watershed cuts along with a theoretical analysis of some of their properties. Extensive evaluation on two types of 3D electron microscopic volumes of neural tissue shows that measures which estimate the non-local consequences of new user inputs achieve performance close to an oracle endowed with complete knowledge of the ground truth.

[1]  Ullrich Köthe,et al.  Carving: Scalable Interactive Segmentation of Neural Volume Electron Microscopy Images , 2011, MICCAI.

[2]  Subhash Suri,et al.  Stochastic Minimum Spanning Trees and Related Problems , 2011, ANALCO.

[3]  Luc Vincent,et al.  Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Camille Couprie,et al.  Power Watershed: A Unifying Graph-Based Optimization Framework , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Christoph H. Lampert,et al.  Enforcing topological constraints in random field image segmentation , 2011, CVPR 2011.

[6]  Marie-Pierre Jolly,et al.  Interactive Graph Cuts for Optimal Boundary and Region Segmentation of Objects in N-D Images , 2001, ICCV.

[7]  Jiebo Luo,et al.  iCoseg: Interactive co-segmentation with intelligent scribble guidance , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[8]  Christophe Chefd'Hotel,et al.  Random Walk and Front Propagation on Watershed Adjacency Graphs for Multilabel Image Segmentation , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[9]  W. Denk,et al.  Serial Block-Face Scanning Electron Microscopy to Reconstruct Three-Dimensional Tissue Nanostructure , 2004, PLoS biology.

[10]  H. Bodlaender,et al.  A Note on the Complexity of Network Reliability Problems , 2004 .

[11]  Bernard Chazelle,et al.  A minimum spanning tree algorithm with inverse-Ackermann type complexity , 2000, JACM.

[12]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[13]  Leo Grady,et al.  Fast approximate Random Walker segmentation using eigenvector precomputation , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[14]  Leo Grady,et al.  Random Walks for Image Segmentation , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Olivier Juan,et al.  Active Graph Cuts , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[16]  G. Knott,et al.  Supervoxel-Based Segmentation of EM Image Stacks with Learned Shape Features , 2010 .

[17]  Ghassan Hamarneh,et al.  Active Learning for Interactive 3D Image Segmentation , 2011, MICCAI.

[18]  R. Lotufo,et al.  MINIMAL SET OF MARKERS FOR THE WATERSHED TRANSFORM , 2002 .

[19]  Jean Stawiaski,et al.  A Stochastic Evaluation of the Contour Strength , 2010, DAGM-Symposium.

[20]  Dominique Jeulin,et al.  Stochastic watershed segmentation , 2007, ISMM.

[21]  Pushmeet Kohli,et al.  Learning an interactive segmentation system , 2010, ICVGIP '10.

[22]  George Papandreou,et al.  Perturb-and-MAP random fields: Using discrete optimization to learn and sample from energy models , 2011, 2011 International Conference on Computer Vision.

[23]  Pushmeet Kohli,et al.  Measuring Uncertainty in Graph Cut Solutions - Efficiently Computing Min-marginal Energies Using Dynamic Graph Cuts , 2006, ECCV.

[24]  G. Knott,et al.  Serial Section Scanning Electron Microscopy of Adult Brain Tissue Using Focused Ion Beam Milling , 2008, The Journal of Neuroscience.

[25]  Gilles Bertrand,et al.  Watershed Cuts: Minimum Spanning Forests and the Drop of Water Principle , 2009, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  James M. Rehg,et al.  Combining Self Training and Active Learning for Video Segmentation , 2011, BMVC.

[27]  Harold N. Gabow,et al.  Two Algorithms for Generating Weighted Spanning Trees in Order , 1977, SIAM J. Comput..