Robust image segmentation using learned priors

A novel parametric deformable model of a goal object controlled by shape and appearance priors learned from co-aligned training images is introduced. The shape prior is built in a linear space of vectors of distances to the training boundaries from their common centroid. The appearance prior is modeled with a spatially homogeneous 2nd-order Markov-Gibbs random field (MGRF) of gray levels within each training boundary. Geometric structure of the MGRF and Gibbs potentials are analytically estimated from the training data. To accurately separate goal objects from arbitrary background, the deformable model is evolved by solving an Eikonal partial differential equation with a speed function combining the shape and appearance priors and the current appearance model. The latter represents empirical gray level marginals inside and outside an evolving boundary with adaptive linear combinations of discrete Gaussians (LCDG). The analytical shape and appearance priors and a simple Expectation-Maximization procedure for getting the object and background LCDGs, make our segmentation considerably faster than most of the known counterparts. Experiments with various images confirm robustness, accuracy, and speed of our approach.

[1]  Thomas Brox,et al.  Nonlinear Matrix Diffusion for Optic Flow Estimation , 2002, DAGM-Symposium.

[2]  Timothy F. Cootes,et al.  Statistical models of appearance for medical image analysis and computer vision , 2001, SPIE Medical Imaging.

[3]  Dimitris N. Metaxas,et al.  MetaMorphs: Deformable shape and texture models , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[4]  W. Eric L. Grimson,et al.  A shape-based approach to the segmentation of medical imagery using level sets , 2003, IEEE Transactions on Medical Imaging.

[5]  Martin Styner,et al.  Automatic and Robust Computation of 3D Medial Models Incorporating Object Variability , 2003, International Journal of Computer Vision.

[6]  Guido Gerig,et al.  Multiscale medial shape-based analysis of image objects , 2003, Proc. IEEE.

[7]  J. Sethian,et al.  A Fast Level Set Method for Propagating Interfaces , 1995 .

[8]  Olivier D. Faugeras,et al.  Statistical shape influence in geodesic active contours , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[9]  Timothy F. Cootes,et al.  Active Shape Models-Their Training and Application , 1995, Comput. Vis. Image Underst..

[10]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[11]  Koenraad Van Leemput,et al.  A unifying framework for partial volume segmentation of brain MR images , 2003, IEEE Transactions on Medical Imaging.

[12]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[13]  Dinggang Shen,et al.  An Adaptive-Focus Deformable Model Using Statistical and Geometric Information , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[14]  Lawrence H. Staib,et al.  An integrated approach to boundary finding in medical images , 1994, Proceedings of IEEE Workshop on Biomedical Image Analysis.

[15]  Rachid Deriche,et al.  Active unsupervised texture segmentation on a diffusion based feature space , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[16]  Daniel Cremers,et al.  Nonlinear Shape Statistics in Mumford-Shah Based Segmentation , 2002, ECCV.

[17]  Tao Zhang,et al.  Model-based segmentation of medical imagery by matching distributions , 2005, IEEE Transactions on Medical Imaging.

[18]  W. Eric L. Grimson,et al.  Coupling Statistical Segmentation and PCA Shape Modeling , 2004, MICCAI.

[19]  Georgy L. Gimel'farb,et al.  Accurate Identification of a Markov-Gibbs Model for Texture Synthesis by Bunch Sampling , 2007, CAIP.

[20]  Cordelia Schmid,et al.  A performance evaluation of local descriptors , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Georgy L. Gimel'farb,et al.  Image Textures and Gibbs Random Fields , 1999, Computational Imaging and Vision.

[22]  Timothy F. Cootes,et al.  A mixture model for representing shape variation , 1999, Image Vis. Comput..

[23]  Fiona F. Evans.  Detecting fish in underwater video using the EM algorithm , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).

[24]  Georgy L. Gimel'farb,et al.  Image segmentation with a parametric deformable model using shape and appearance priors , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Alex Pentland,et al.  Closed-form solutions for physically-based shape modeling and recognition , 1991, Proceedings. 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[26]  Christopher J. Taylor,et al.  Model-Based Interpretation of 3D Medical Images , 1993, BMVC.

[27]  Stefano Soatto,et al.  A Pseudo-distance for Shape Priors in Level Set Segmentation , 2003 .

[28]  James S. Duncan,et al.  Boundary Finding with Parametrically Deformable Models , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[29]  Nikos Paragios,et al.  Shape Priors for Level Set Representations , 2002, ECCV.

[30]  Guillermo Sapiro,et al.  Geodesic Active Contours , 1995, International Journal of Computer Vision.

[31]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[32]  James S. Duncan,et al.  3D image segmentation of deformable objects with joint shape-intensity prior models using level sets , 2004, Medical Image Anal..

[33]  Tony F. Chan,et al.  Active contours without edges , 2001, IEEE Trans. Image Process..

[34]  Yunmei Chen,et al.  On the incorporation of shape priors into geometric active contours , 2001, Proceedings IEEE Workshop on Variational and Level Set Methods in Computer Vision.

[35]  Rachid Deriche,et al.  Geodesic Active Contours and Level Sets for the Detection and Tracking of Moving Objects , 2000, IEEE Trans. Pattern Anal. Mach. Intell..