My research has primarily focused on image
segmentation, data clustering, learning and filtering using techniques
from graph theory, combinatorial topology and partial differential
equations. Other interests include pattern/object recognition,
applied mathematics, non-uniform data processing, image registration,
cellular automata, robotics and emergent phenomena.
Software
The Graph
Analysis Toolbox for MATLAB was written as a by-product of my PhD
thesis. My intention was to allow for flexible representation and
analysis of data associated with a graph, specifically slanted toward
computer vision applications. You can read some reviews at the
Mathworks page.
I have written a short MATLAB function that runs the random
walker image segmentation algorithm as an add-on to the above Graph
Analysis Toolbox. The files contain a function to run the random
walker algorithm and a script demonstrating its usage. The code may
be found here. To see
an (html) demo of the random walker algorithm, click here.
Upcoming
1) June 30th - July 2nd, 2010, Trois-Rivières, Quebec, Canada - ICISP Recent Activities
In Press
1) Camille Couprie, Leo Grady, Laurent Najman and Hugues Talbot, "Power Watersheds: A New Image Segmentation Framework Extending Graph Cuts, Random Walker and Optimal Spanning Forest", Accepted to ICCV 2009.
2) Marie-Pierre Jolly, Hui Xue, Leo Grady and Jens Guehring "Combining Registration and Minimum Surfaces for the Segmentation of the Left Ventricle in Cardiac Cine MR Images", Accepted to MICCAI 2009.
3) Dheeraj Singaraju, Leo Grady and René Vidal, "P-Brush: Continuous Valued MRFs with Normed Pairwise Distributions for Image Segmentation", Accepted to CVPR 2009.
PDF
4) Leo Grady, "Minimal Surfaces Extend Shortest Path Segmentation Methods to 3D", Accepted to IEEE Trans. on Pattern Analysis and Machine Intelligence.
PDF
Published (in reverse chronological order)
25) Leo Grady and Christopher Alvino, "Reformulating and Optimizing the Mumford-Shah Functional on a Graph - A Faster, Lower Energy Solution", Proc. of ECCV 2008, Marseille, France, Oct. 2008, pp. 248-261, LNCS Vol. 5302
PDF, BIB
24) Leo Grady, "A Lattice-Preserving Multigrid Method for Solving the Inhomogeneous Poisson Equations used in Image Analysis", Proc. of ECCV 2008, Marseille, France, Oct. 2008, pp. 252-264, LNCS Vol. 5303
PDF, BIB
23) Leo Grady and Marie-Pierre Jolly, "Weights and Topology: A Study of the Effects of Graph Construction on 3D Image Segmentation", Proc. of MICCAI 2008, vol. 1, 2008, pp. 153-161, Sept., New York City, New York.
PDF,
BIB,
Poster (PPT)
22) Leo Grady and Ali Kemal Sinop, "Fast Approximate Random Walker Segmentation Using Eigenvector Precomputation", Proc. of CVPR 2008, Anchorage, Alaska, June 24-26, 2008.
PDF,
BIB,
Poster (PPT)
21) Dheeraj Singaraju, Leo Grady and René Vidal, "Interactive Image Segmentation of Quadratic Energies on Directed Graphs", Proc. of CVPR 2008, Anchorage, Alaska, June 24-26, 2008
PDF,
BIB
20) Marie-Pierre Jolly and Leo Grady, "3D General Lesion Segmentation in CT", Proc. of ISBI 2008, Paris, France, May 14-17 2008. pp. 796-799.
PDF,
BIB
19) Ali Kemal Sinop and Leo Grady, "A Seeded Image Segmentation Framework Unifying Graph Cuts and Random Walker Which Yields A New Algorithm", in Proc. of ICCV 2007, Rio de Janeiro, Brazil, Oct. 14-20, 2007 (Oral presentation)
PDF,
BIB,
ICCV Talk (requires TeX4PPT to view equations)
18) Ali Kemal Sinop and Leo Grady, "Uninitialized, Globally Optimal, Graph-Based Rectilinear Shape Segmentation - The Opposing Metrics Method", In Proc. of ICCV 2007, Rio de Janeiro, Brazil, Oct. 14-20, 2007 (Poster presentation)
PDF,
BIB,
ICCV Poster (requires TeX4PPT to view equations)
17) Osman Bodur, Leo Grady, Arthur Stillman, Randolph Setser, Gareth Funka-Lea, Thomas O'Donnell, "Semi-Automatic Aortic Aneurysm Analysis", in A. Manduca and X.P. Hu (Eds), Proc. SPIE Medical Imaging 2007: Physiology, function, and structure from medical images, 6511
PDF
16) Leo Grady, "Random Walks for Image Segmentation",
IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 28, No. 11, pp. 1768-1783, Nov., 2006.
PDF,
BIB,
MATLAB Code,
Demo (html)
15) Leo Grady, Gareth Funka-Lea, "An Energy Minimization Approach to
the Data Driven Editing of Presegmented Images/Volumes", Proceedings
of MICCAI 2006, vol. 2, 2006, pp. 888-895, Oct., Copenhagen, Denmark.
PDF,
BIB,
Poster (PDF)
14) Ali Kemal Sinop, Leo Grady, "Accurate Banded Graph Cut
Segmentation of Thin Structures Using Laplacian Pyramids", Proceedings of
MICCAI 2006, vol. 2, 2006, pp. 896-903, Oct., Copenhagen, Denmark.
PDF,
BIB,
Poster (PDF)
13) Leo Grady, "Computing Exact Discrete Minimal Surfaces: Extending and
Solving the Shortest Path Problem in 3D with Application to Segmentation",
Proceedings of CVPR 2006, vol. 1, 2006, pp. 69-78, June, New York, New York.
PDF,
BIB,
Code (MATLAB)
12) Leo Grady, "Fast, Quality, Segmentation of Large Volumes -
Isoperimetric Distance Trees", Proceedings of ECCV 2006, vol. 3, 2006,
pp. 449-462, May, Graz, Austria, Springer.
PDF,
BIB,
Poster (PDF)
11) Daniel Cremers, Leo Grady, "Statistical Priors for Efficient Combinatorial
Optimization via Graph Cuts", Proceedings of ECCV 2006, vol. 3, 2006,
pp. 263-274, May, Graz, Austria, Springer.
PDF,
BIB
10) Leo Grady, Yiyong Sun and James Williams, "Three Interactive
Graph-Based Segmentation Methods Applied to Cardiovascular Imaging",
In "Mathematical
Models in Computer Vision: The Handbook", 453-469, ed. Nikos Paragios,
Yunmei Chen, Oliver Faugeras, Springer 2006
PDF,
BIB
9) Leo Grady and Eric L. Schwartz, "Isoperimetric Partitioning: A new
algorithm for graph partitioning", SIAM Journal on Scientific
Computing, vol. 27, no. 6, pp. 1844-1866, June 2006. PDF, BIB
7) Leo Grady, Thomas Schiwietz, Shmuel Aharon, Rudiger Westermann, "Random Walks for Interactive Organ Segmentation in Two and Three Dimensions: Implementation and Validation",
Proceedings of MICCAI 2005, vol. 2, 2005, pp. 773-780, October, Palm Springs, CA, Springer.
PDF,
BIB,
Poster (PDF)
6) Herve Lombaert, Yiyong Sun, Leo Grady, Chenyang Xu "A Multilevel Banded Graph Cuts Method for Fast Image Segmentation",
Proceedings of ICCV 2005, vol. 1, 2005, pp. 259-265, October, Bejing, China, IEEE. PDF (link), BIB
5) Leo Grady, Tolga Tasdizen "A Geometric Multigrid Approach to Solving the 2D Inhomogeneous Laplace Equation with Internal Dirichlet Boundary Conditions",
Proceedings of ICIP 2005, vol. 2, 2005, pp. 642-645, September, Genoa. PDF, BIB, Poster (PDF)
4) Leo Grady, Thomas Schiwietz, Shmuel Aharon , Rudiger Westermann, "Random Walks for Interactive Alpha-Matting",
Proceedings of VIIP 2005, September, Benidorm, Spain pp. 423-429, ACTA Press. PDF,
BIB,
Talk (PDF)
3) Leo Grady, "Multilabel Random Walker Image Segmentation Using Prior Models", in Proceedings of CVPR05, Vol. 1, p. 763-770, San Diego, CA June 2005. PDF, BIB,
Poster (PDF),
Demo (html)
2) Leo Grady and Eric
L. Schwartz. "Faster graph-theoretic image processing via small-world
and quadtree topologies." In Proceedings of CVPR04, pp. 360-365,
Washington, DC, June-July 2004. IEEE.
PDF,
BIB,
Talk (PDF),
Code to generate all figures
1) Leo Grady and Gareth
Funka-Lea, "Multi-Label Image Segmentation for Medical Applications
Based on Graph-Theoretic Electrical Potentials", in Proceedings of the
8th ECCV04, Workshop on Computer Vision Approaches to Medical Image
Analysis and Mathematical Methods in Biomedical Image Analysis, p. 230-245, May
15th, 2004, Prague, Czech Republic, Springer-Verlag. PDF, BIB, Poster (PDF),
MATLAB Code,
Demo (html)
Technical reports
1) Leo Grady and Eric L. Schwartz, "The Graph Analysis
Toolbox: A User's Manual", which serves as the user's manual for the Graph Analysis Toolbox. Technical Report CAS/CNS-TR-03-021, Department of Cognitive and Neural Systems, Boston University, Boston, MA, Aug. 2003.
PDF, BIB
Here are a set of links to sites that I have found very useful.
I tried to limit myself to links that visitors probably weren't aware of
(e.g., not Google, Mathworld or Slashdot). All the links
below
point to sites with content.
Research related links Natural
Image Database This database contains
many high resolution (grayscale) natural images. They use a home-grown
image format that I wrote a MATLAB function to read, which may
be found here